id
large_stringlengths
23
28
split
large_stringclasses
1 value
modality
large_stringclasses
1 value
turn_type
large_stringclasses
1 value
dialogue
listlengths
1
8
input
dict
streaming
dict
target
dict
taxonomy
dict
quality
dict
source
dict
metadata
dict
audio_spokenwoz_v02_007264
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, good evening. they are customer service of cambridge.", "turn_id": 2 }, { "role": "user", "text": "sure, i'm traveling to campus. i'm looking for some information.", "turn_id": 3 },...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, good evening. they are customer service of cambridge.\nChunk 3: sure, i'm traveling to campus. i'm looking for some information.\nChunk 4: wow, thing. i have no car there, so i prefer to book a taxi.\nChunk 5: well, could you please book a taxi for me.\nChunk 6: well, i...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help book that. Could you provide the time?", "reasoning": "Across the dialogue, the user is searching for information. Key context: yes, good evening; they are customer service of cambridge; sure, i'm traveling to campus; i'm looking for some information. The answer should focus on the latest us...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0001", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007265
train
audio
multi_turn
[ { "role": "user", "text": "hello. how.", "turn_id": 1 }, { "role": "assistant", "text": "i'm doing more. thank you.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello. how.\nChunk 2: i'm doing more. thank you.", "dialogue_text": "Chunk 1: hello. how.\nChunk 2: i'm doing more. thank you.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chunks.", "length_bucket": "short", "nu...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. how.", "role": "user", "streaming_reasoning": "The user mentions Hello. how. It is not yet clear whether the user needs the full scope of the user's request. The ...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user discusses \"hello. how.\" over 2 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user discusses \...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0982", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000254
train
audio
multi_turn
[ { "role": "user", "text": "He was in deep converse with the clerk and entered the hall holding him by the arm.", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: He was in deep converse with the clerk and entered the hall holding him by the arm.", "dialogue_text": "Chunk 1: He was in deep converse with the clerk and entered the hall holding him by the arm.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "He was in deep converse with the clerk and entered the hall holding him by the arm.", "role": "user", "streaming_reasoning": "The user mentions He was in deep converse w...
{ "answer": "It seems they were discussing something important. The noise of the traffic might have urged them to stick closer to hear each other.", "reasoning": "Across the dialogue, the user discusses \"He was in deep converse with the clerk and entered the hall.\" over 1 turns. The answer should respond to the l...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SD-Eval", "dialogue_id": "61-70970-0007-traffic", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007266
train
audio
multi_turn
[ { "role": "user", "text": "i'm great. and how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for a train.", "turn_id": 2 }, { "role": "user", "text": "i will depart from birmingham new street.", "turn_id": 3 }, { "role": "assistant", "t...
{ "chunk_text": "Chunk 1: i'm great. and how are you.\nChunk 2: i'm looking for a train.\nChunk 3: i will depart from birmingham new street.\nChunk 4: i'm headed for cambridge.\nChunk 5: i would love to leave on sunday after quarter past 4.\nChunk 6: i will hold thank you.\nChunk 7: you are welcome.\nChunk 8: to rate...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm great. and how are you.", "role": "user", "streaming_reasoning": "The user mentions I'm great. and how are you. It is not yet clear whether the user needs the full s...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: and how are you; i'm looking for a train; i will depart from birmingham new street; i'm headed for cambridge. The answer should focus on the latest user turn wh...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1151", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007267
train
audio
multi_turn
[ { "role": "user", "text": "0 4, 4.", "turn_id": 1 }, { "role": "assistant", "text": "1 5 time.", "turn_id": 2 }, { "role": "user", "text": "4, 3, 8, 3.", "turn_id": 3 }, { "role": "assistant", "text": "7 3 1.", "turn_id": 4 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: 0 4, 4.\nChunk 2: 1 5 time.\nChunk 3: 4, 3, 8, 3.\nChunk 4: 7 3 1.\nChunk 5: no, that will be fine. thank you. i'm also looking for a restaurant in a moderate price for serving seafood. i'd like to eat fish.\nChunk 6: the area is fine.\nChunk 7: thank you.\nChunk 8: can you maybe find someth...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "0 4, 4.", "role": "user", "streaming_reasoning": "The user mentions 0 4, 4. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "I can help with the restaurant. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for restaurant in a moderate price for serving seafood. Key context: no, that will be fine; i'm also looking for a restaurant in a moderate price for serving seafood; i'd like to eat fis...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2060", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002190
train
audio
multi_turn
[ { "role": "user", "text": "Human: I don't think so. Ha, ha, ha! Top bowlers made good money in the 1960's!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: They sure did. I would rather bowl than play football. Fewer concussions.", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: Human: I don't think so. Ha, ha, ha! Top bowlers made good money in the 1960's!\nChunk 2: Assistant: They sure did. I would rather bowl than play football. Fewer concussions.\nChunk 3: Human: For sure. Better for your body in the long run!", "dialogue_text": "Chunk 1: Human: I don't think ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I don't think so. Ha, ha, ha! Top bowlers made good money in the 1960's!", "role": "user", "streaming_reasoning": "The user mentions asking for recommendations ab...
{ "answer": "Except for the beer and pizza. That could be a problem. No problem sharing a restaurant with the cheerleaders.", "reasoning": "Across the dialogue, the user discusses \"I don't think so. Ha, ha, ha! Top bowlers made good money.\" over 3 turns. The answer should respond to the latest user turn naturally...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_1094f2c3-ca03-4de3-9db1-d58ccf8977bc", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007268
train
audio
multi_turn
[ { "role": "user", "text": "uh, yes. um, i like to book for four people.", "turn_id": 1 }, { "role": "assistant", "text": "and on thursday this week.", "turn_id": 2 }, { "role": "user", "text": "i like to arrive here by 1130.", "turn_id": 3 }, { "role": "assistant"...
{ "chunk_text": "Chunk 1: uh, yes. um, i like to book for four people.\nChunk 2: and on thursday this week.\nChunk 3: i like to arrive here by 1130.\nChunk 4: how about saturday does that work.\nChunk 5: it's jenny west.\nChunk 6: okay. uh, it's j e double ny jenny and the w e st west.\nChunk 7: yes. also i'm looking...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, yes. um, i like to book for four people.", "role": "user", "streaming_reasoning": "The user mentions Uh, yes. um, i like to book for four people. It is not yet clear...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: um, i like to book for four people; and on thursday this week; i like to arrive here by 1130; how about saturday does that work. The answer should f...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2915", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002191
train
audio
multi_turn
[ { "role": "user", "text": "Human: There are a lot of different kinds of football. Rugby, Soccer, Australian football are some of them.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah, it gets a little bit confusing, considering I call soccer, soccer! The highest score ever ...
{ "chunk_text": "Chunk 1: Human: There are a lot of different kinds of football. Rugby, Soccer, Australian football are some of them.\nChunk 2: Assistant: Yeah, it gets a little bit confusing, considering I call soccer, soccer! The highest score ever in a football game was in 1916, when Georgia Tech defeated Cumberla...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: There are a lot of different kinds of football. Rugby, Soccer, Australian football are some of them.", "role": "user", "streaming_reasoning": "The user mentions t...
{ "answer": "Yeah! Huge loss! It was very nice talking to you as well!", "reasoning": "Across the dialogue, the user is asking for help with human: there are a lot of different kinds of football. Key context: Human: There are a lot of different kinds of football; Rugby, Soccer, Australian football are some of them;...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_7f20abce-b2d4-4682-a407-01f4e8ac6f27", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002192
train
audio
multi_turn
[ { "role": "user", "text": "Human: yeah true. Do you know who voices the Hulk?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Don't know. The Hulk is the big green fellow?", "turn_id": 2 }, { "role": "user", "text": "Human: Yes that is him. It was played by Lou F...
{ "chunk_text": "Chunk 1: Human: yeah true. Do you know who voices the Hulk?\nChunk 2: Assistant: Don't know. The Hulk is the big green fellow?\nChunk 3: Human: Yes that is him. It was played by Lou Ferigno once and now he stills does the voice for the character.", "dialogue_text": "Chunk 1: Human: yeah true. Do yo...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: yeah true. Do you know who voices the Hulk?", "role": "user", "streaming_reasoning": "The user mentions Human: yeah true. Do you know who voices the Hulk?. It is ...
{ "answer": "That's great! Good for Lou! The man is deaf in one ear.", "reasoning": "Across the dialogue, the user discusses \"yeah true. Do you know who voices the.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across t...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_8c18c55b-0d2f-45a6-af03-586e36bd4a23", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007269
train
audio
multi_turn
[ { "role": "user", "text": "hello. and all that. hello. but i'm not understood.", "turn_id": 1 }, { "role": "assistant", "text": "i'm fine. thanks all of you.", "turn_id": 2 }, { "role": "user", "text": "you are speaking worth harry harden.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hello. and all that. hello. but i'm not understood.\nChunk 2: i'm fine. thanks all of you.\nChunk 3: you are speaking worth harry harden.", "dialogue_text": "Chunk 1: hello. and all that. hello. but i'm not understood.\nChunk 2: i'm fine. thanks all of you.\nChunk 3: you are speaking worth...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. and all that. hello. but i'm not understood.", "role": "user", "streaming_reasoning": "The user mentions Hello. and all that. hello. but i'm not understood. It is...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user discusses \"hello. and all that. hello. but i'm not.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the d...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0812", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002193
train
audio
multi_turn
[ { "role": "user", "text": "Human: There is a wreck it ralph game?that would be merchandise before the movie.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah its originally a game I think, a really old arcade game, did you watch the movie frozen?", "turn_id": 2 }, { ...
{ "chunk_text": "Chunk 1: Human: There is a wreck it ralph game?that would be merchandise before the movie.\nChunk 2: Assistant: Yeah its originally a game I think, a really old arcade game, did you watch the movie frozen?\nChunk 3: Human: Parts of Frozen. Olaff the snow man is funny.", "dialogue_text": "Chunk 1: H...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: There is a wreck it ralph game?that would be merchandise before the movie.", "role": "user", "streaming_reasoning": "The user mentions talking about Human, There....
{ "answer": "Yeah Olaf is a funny one, cool fact about the movie but its the first animated Disney film directed by a woman, anyway its been great chatting with you I think Im going to watch a Disney movie now.", "reasoning": "Across the dialogue, the user discusses \"There is a wreck it ralph game?that would be me...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_04724774-78d7-4a2c-aebf-7e1116a81c52", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007270
train
audio
multi_turn
[ { "role": "user", "text": "that's perfect.", "turn_id": 1 }, { "role": "assistant", "text": "6 38 is no problem.", "turn_id": 2 }, { "role": "user", "text": "yes, please, for four people.", "turn_id": 3 }, { "role": "assistant", "text": "my id number is 4 2, 5...
{ "chunk_text": "Chunk 1: that's perfect.\nChunk 2: 6 38 is no problem.\nChunk 3: yes, please, for four people.\nChunk 4: my id number is 4 2, 5 3.\nChunk 5: 3, 2, 0, 6.\nChunk 6: 3, 4, 5, 7.\nChunk 7: 5 7, 6 1.\nChunk 8: yes, please.", "dialogue_text": "Chunk 1: that's perfect.\nChunk 2: 6 38 is no problem.\nChunk...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "that's perfect.", "role": "user", "streaming_reasoning": "The user mentions That's perfect. It is not yet clear whether the user needs the full scope of the user's reque...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is reporting a problem with that's perfect. Key context: that's perfect; 6 38 is no problem; yes, please, for four people; my id number is 4 2, 5 3. The answer should focus on the l...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2108", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002194
train
audio
multi_turn
[ { "role": "user", "text": "Human: Actually yes, I like Brady a lot and you?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Nice same here. DO you know what his favorite ice cream flavour is?", "turn_id": 2 }, { "role": "user", "text": "Human: Yes it is avocado a...
{ "chunk_text": "Chunk 1: Human: Actually yes, I like Brady a lot and you?\nChunk 2: Assistant: Nice same here. DO you know what his favorite ice cream flavour is?\nChunk 3: Human: Yes it is avocado and I am not surprised the guy is very health conscious", "dialogue_text": "Chunk 1: Human: Actually yes, I like Brad...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Actually yes, I like Brady a lot and you?", "role": "user", "streaming_reasoning": "The user mentions Human: Actually yes, I like Brady a lot and you?. It is not ...
{ "answer": "Yes exactly. He wrote a book also so he is an author as well now", "reasoning": "Across the dialogue, the user discusses \"Actually yes, I like Brady a lot and.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_f8415da7-210d-4525-a23e-c59c8c8aea71", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007271
train
audio
multi_turn
[ { "role": "user", "text": "well, i want to know the departure time of the train.", "turn_id": 1 }, { "role": "assistant", "text": "got it manual the price of that one.", "turn_id": 2 }, { "role": "user", "text": "got that manual train id.", "turn_id": 3 }, { "role...
{ "chunk_text": "Chunk 1: well, i want to know the departure time of the train.\nChunk 2: got it manual the price of that one.\nChunk 3: got that manual train id.\nChunk 4: okay, got it. thank you very much. i can get off of the train. information.\nChunk 5: yes. um, i'm also looking for a place to stay.\nChunk 6: we...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "well, i want to know the departure time of the train.", "role": "user", "streaming_reasoning": "The user mentions Well, i want to know the departure time of the train. I...
{ "answer": "I can help with the hotel. Could you share the area, price?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: well, i want to know the departure time of the train; got it manual the price of that one; got that manual train id; okay, got it. The answer should foc...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1141", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002195
train
audio
multi_turn
[ { "role": "user", "text": "Human: I think I'd be reluctant to pay him at that rate. I hope the Redskins get their money's worth.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: They did not! In fact, the young kid that took over at QB for Kansas City won the NFL MVP this year!!"...
{ "chunk_text": "Chunk 1: Human: I think I'd be reluctant to pay him at that rate. I hope the Redskins get their money's worth.\nChunk 2: Assistant: They did not! In fact, the young kid that took over at QB for Kansas City won the NFL MVP this year!!\nChunk 3: Human: That's awesome. He was probably somewhat cheaper t...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I think I'd be reluctant to pay him at that rate. I hope the Redskins get their money's worth.", "role": "user", "streaming_reasoning": "The user mentions talking...
{ "answer": "Much cheaper! They were doing decent but then Alex Smith got hurt and his backup did too. They wound up missing the playoffs.", "reasoning": "Across the dialogue, the user discusses \"I think I'd be reluctant to pay him at that rate. I hope.\" over 3 turns. The answer should respond to the latest user ...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_0081ed02-9b2e-419f-b962-eb7c54e29127", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002196
train
audio
multi_turn
[ { "role": "user", "text": "Human: He is close - 100 billion dollars. With bruce wayne at 80.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I guess you need a lot of money to be a superhero these days. Do you know if they are going to make a sequel to the movie?", "turn_id"...
{ "chunk_text": "Chunk 1: Human: He is close - 100 billion dollars. With bruce wayne at 80.\nChunk 2: Assistant: I guess you need a lot of money to be a superhero these days. Do you know if they are going to make a sequel to the movie?\nChunk 3: Human: I don't know, I would think so. It was really popular.", "dialo...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: He is close - 100 billion dollars. With bruce wayne at 80.", "role": "user", "streaming_reasoning": "The user mentions talking about 100, 80, Human. It is not yet...
{ "answer": "Seems like I saw the character, Black Panther, in the movie Captain America-Civil War. Was he in it?", "reasoning": "Across the dialogue, the user discusses \"He is close - 100 billion dollars. With bruce wayne at.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_00f2662b-0f83-4e00-b8e5-e731638f3690", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007272
train
audio
multi_turn
[ { "role": "user", "text": "good morning. how are you.", "turn_id": 1 }, { "role": "assistant", "text": "oh, i'm doing great. thank you.", "turn_id": 2 }, { "role": "user", "text": "i am looking for a place to go in town.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: good morning. how are you.\nChunk 2: oh, i'm doing great. thank you.\nChunk 3: i am looking for a place to go in town.\nChunk 4: um something with this swimming pool, please.\nChunk 5: thank you very much.\nChunk 6: oh, that sounds like an interesting place.\nChunk 7: well, i would like to k...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "good morning. how are you.", "role": "user", "streaming_reasoning": "The user mentions Good morning. how are you. It is not yet clear whether the user needs the full sco...
{ "answer": "Sure. I can help with the area; first I need to identify the right attraction option.", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: good morning; how are you; oh, i'm doing great; i am looking for a place to go in town. The answer should focus on the l...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1317", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007273
train
audio
multi_turn
[ { "role": "user", "text": "hi, good day. i'm hoping that you can help me.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm busy planning a trip to cambridge and i was hoping that you'll be able to give you some information.", "turn_id": 2 }, { "role": "user", "text"...
{ "chunk_text": "Chunk 1: hi, good day. i'm hoping that you can help me.\nChunk 2: yes, i'm busy planning a trip to cambridge and i was hoping that you'll be able to give you some information.\nChunk 3: uh first of all at a place so i prefer a guest house and it should be in the moderate price range i also don't", ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, good day. i'm hoping that you can help me.", "role": "user", "streaming_reasoning": "The user mentions Hi, good day. i'm hoping that you can help me. It is not yet c...
{ "answer": "I can help with the hotel. Could you share the area?", "reasoning": "Across the dialogue, the user discusses \"hi, good day. i'm hoping that you can help.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2929", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007274
train
audio
multi_turn
[ { "role": "user", "text": "i sse.", "turn_id": 1 }, { "role": "assistant", "text": "patello b ot.", "turn_id": 2 }, { "role": "user", "text": "e ll o.", "turn_id": 3 }, { "role": "assistant", "text": "ok.", "turn_id": 4 }, { "role": "user", "te...
{ "chunk_text": "Chunk 1: i sse.\nChunk 2: patello b ot.\nChunk 3: e ll o.\nChunk 4: ok.\nChunk 5: okay. um, i also am looking to attend a local attraction located downtown.\nChunk 6: oh, okay. do you have the phone number for that.\nChunk 7: and the address.\nChunk 8: okay, and the post code.", "dialogue_text": "C...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i sse.", "role": "user", "streaming_reasoning": "The user mentions I sse. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "Sure. I can provide the phone, address, postcode for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for patello b ot. Key context: patello b ot; um, i also am looking to attend a local attraction located downtown; do you have the phone number for that; and th...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2376", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002197
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah it would be very confusing to me. The talkshow host John Stewart was a skilled soccer player in college and he even represented the US at the Pan-American games in Brazil.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I didn't realize he ...
{ "chunk_text": "Chunk 1: Human: Yeah it would be very confusing to me. The talkshow host John Stewart was a skilled soccer player in college and he even represented the US at the Pan-American games in Brazil.\nChunk 2: Assistant: I didn't realize he was that old. I don't think I remember him until the 1990s.\nChunk ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah it would be very confusing to me. The talkshow host John Stewart was a skilled soccer player in college and he even represented the US at the Pan-American games in Brazi...
{ "answer": "Yes. He is valued at 120 million euro! Big money!", "reasoning": "Across the dialogue, the user is asking for help with human: yeah it would be very confusing to me. Key context: Human: Yeah it would be very confusing to me; The talkshow host John Stewart was a skilled soccer player in college and he e...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_f5a9b24a-fce9-4733-b627-cdd25de0d894", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007275
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "good day. i am looking for information about a train in cambridge.", "turn_id": 2 }, { "role": "user", "text": "i am looking for a train that departs from cambridge and goes to stanford...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: good day. i am looking for information about a train in cambridge.\nChunk 3: i am looking for a train that departs from cambridge and goes to stanford airport.\nChunk 4: and it should leave after. a quota. 8 pm on monday.\nChunk 5: okay, i would like to book 5.5 egg.\...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for information about a train in cambridge. Key context: i am looking for information about a train in cambridge; i am looking for a train that depart...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2653", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002198
train
audio
multi_turn
[ { "role": "user", "text": "Human: I read a lot of Marvel and DC when I was a kid. I have not kept up. I liked the Batman book character rather than the brooding one in the movies. They have been around since 1933.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes that is defin...
{ "chunk_text": "Chunk 1: Human: I read a lot of Marvel and DC when I was a kid. I have not kept up. I liked the Batman book character rather than the brooding one in the movies. They have been around since 1933.\nChunk 2: Assistant: Yes that is definitely a long time. I'm pretty although and even I know that DC stan...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I read a lot of Marvel and DC when I was a kid. I have not kept up. I liked the Batman book character rather than the brooding one in the movies. They have been around since ...
{ "answer": "No I'm shocked that they allow people to read those Comics because I know a lot of them are worth money too, I want to read the Marvel published \"generic comic book\" though it sounds really boring but it's probably funny", "reasoning": "Across the dialogue, the user is wanting to book character rathe...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_a8241ef5-654d-4c8d-8d63-0594d3ebb26f", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007276
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "uh yes i'm looking for um a restaurant in the less expensive price range we're like i've been on the east side of the city", "turn_id": 2 }, { "role": "user", "text": "for quite a bit of food ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: uh yes i'm looking for um a restaurant in the less expensive price range we're like i've been on the east side of the city\nChunk 3: for quite a bit of food could i is it possible to get something on the other side of town that might serve um kind\nChunk 4: of like pass you ...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "Sure. I can provide the postcode for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for now actually i just i think maybe if i just get the postal code dot org. Key context: now actually i just i think maybe if i just get the postal code dot org. The answer s...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "hard", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1677", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007277
train
audio
multi_turn
[ { "role": "user", "text": "i am actually looking for a particular um attraction.", "turn_id": 1 }, { "role": "assistant", "text": "is called. brighton house gallery.", "turn_id": 2 }, { "role": "user", "text": "can i get the postal code, please.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: i am actually looking for a particular um attraction.\nChunk 2: is called. brighton house gallery.\nChunk 3: can i get the postal code, please.\nChunk 4: that's perfect. can i also get the entrance fee, please.\nChunk 5: oh, that's excellent news. thank you.\nChunk 6: yes, i'm looking for tr...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i am actually looking for a particular um attraction.", "role": "user", "streaming_reasoning": "The user mentions I am actually looking for a particular um attraction. I...
{ "answer": "I can help with the train. Could you share the day, time?", "reasoning": "Across the dialogue, the user is searching for particular um attraction. Key context: i am actually looking for a particular um attraction; brighton house gallery; can i get the postal code, please; that's perfect. The answer sho...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3141", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007278
train
audio
multi_turn
[ { "role": "user", "text": "i prefer to be in the west of cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "mm. okay. may i know the address of this watch.", "turn_id": 2 }, { "role": "user", "text": "so it's great. and how about the phone number of this church.", ...
{ "chunk_text": "Chunk 1: i prefer to be in the west of cambridge.\nChunk 2: mm. okay. may i know the address of this watch.\nChunk 3: so it's great. and how about the phone number of this church.\nChunk 4: okay, let me write it down first.\nChunk 5: um may i also know the post code of this college.\nChunk 6: okay, i...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i prefer to be in the west of cambridge.", "role": "user", "streaming_reasoning": "The user mentions I prefer to be in the west of cambridge. It is not yet clear whether...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for particular hole in cambridge. Key context: i prefer to be in the west of cambridge; may i know the address of this watch; so it's great; and how about the phone number ...
{ "category": "education", "subcategory": "course_planning", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1919", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007279
train
audio
multi_turn
[ { "role": "user", "text": "yes, i'm looking for a train leave on thursday.", "turn_id": 1 }, { "role": "assistant", "text": "okay, great. thank you.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: yes, i'm looking for a train leave on thursday.\nChunk 2: okay, great. thank you.", "dialogue_text": "Chunk 1: yes, i'm looking for a train leave on thursday.\nChunk 2: okay, great. thank you.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually rev...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, i'm looking for a train leave on thursday.", "role": "user", "streaming_reasoning": "The user mentions Yes, i'm looking for a train leave on thursday. It is not yet...
{ "answer": "I can help with the train. Could you share the departure, destination, time?", "reasoning": "Across the dialogue, the user is searching for train leave on thursday. Key context: yes, i'm looking for a train leave on thursday; okay, great. The answer should focus on the latest user turn while incorporat...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0381", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007280
train
audio
multi_turn
[ { "role": "user", "text": "um i'm going to cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "okay, thank you.", "turn_id": 2 }, { "role": "user", "text": "yes, please make a reservation for us.", "turn_id": 3 }, { "role": "assistant", "text": "hmm, ...
{ "chunk_text": "Chunk 1: um i'm going to cambridge.\nChunk 2: okay, thank you.\nChunk 3: yes, please make a reservation for us.\nChunk 4: hmm, my number should be 1 8 3 8.\nChunk 5: 8 3 9 3.\nChunk 6: 8 2 double 8.\nChunk 7: 2, 7, 3, 4.\nChunk 8: the attraction should be the type of museums, i suppose.", "dialogue...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um i'm going to cambridge.", "role": "user", "streaming_reasoning": "The user mentions Um i'm going to cambridge. It is not yet clear whether the user needs the full sco...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is wanting to book um i'm going to cambridge. Key context: um i'm going to cambridge; okay, thank you; yes, please make a reservation for us; hmm, my number should be 1 8 3 8. The answer should focus...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0377", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007281
train
audio
multi_turn
[ { "role": "user", "text": "okay. and what is the post code.", "turn_id": 1 }, { "role": "assistant", "text": "okay, and the phone number.", "turn_id": 2 }, { "role": "user", "text": "okay, alright, um i'm also looking to book a taxi.", "turn_id": 3 }, { "role": "a...
{ "chunk_text": "Chunk 1: okay. and what is the post code.\nChunk 2: okay, and the phone number.\nChunk 3: okay, alright, um i'm also looking to book a taxi.\nChunk 4: i wanted to leave the attraction 30 minutes after 9.\nChunk 5: um that's 1 7 9.\nChunk 6: 2, 4, 1.\nChunk 7: 8, 7, 5 7.\nChunk 8: can i get the number...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. and what is the post code.", "role": "user", "streaming_reasoning": "The user mentions Okay. and what is the post code. It is not yet clear whether the user needs ...
{ "answer": "Sure. I can provide the phone for the matching taxi option.", "reasoning": "Across the dialogue, the user is wanting to book taxi. Key context: and what is the post code; okay, and the phone number; okay, alright, um i'm also looking to book a taxi; i wanted to leave the attraction 30 minutes after 9. ...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3766", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002199
train
audio
multi_turn
[ { "role": "user", "text": "Human: do you read books? I can't believe the FDA burned about 6 tonnes of actual books", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Interesting. Do you know why?", "turn_id": 2 }, { "role": "user", "text": "Human: I think it was an ...
{ "chunk_text": "Chunk 1: Human: do you read books? I can't believe the FDA burned about 6 tonnes of actual books\nChunk 2: Assistant: Interesting. Do you know why?\nChunk 3: Human: I think it was an act of censorship because the books were not factual, but that still seems like an extreme thing to do", "dialogue_t...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: do you read books? I can't believe the FDA burned about 6 tonnes of actual books", "role": "user", "streaming_reasoning": "The user mentions wanting to book 6, Hu...
{ "answer": "Weird, so they were fiction books?", "reasoning": "Across the dialogue, the user is wanting to book human: do you read books. Key context: Human: do you read books; I can't believe the FDA burned about 6 tonnes of actual books Assistant: Interesting; Do you know why; Human: I think it was an act of cen...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "explain_cause" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_1b1374aa-5e21-48be-9629-9b28498fae98", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007282
train
audio
multi_turn
[ { "role": "user", "text": "sure is ni double k i.", "turn_id": 1 }, { "role": "assistant", "text": "b r o w n n.", "turn_id": 2 }, { "role": "user", "text": "yes, you got it, nikki brown.", "turn_id": 3 }, { "role": "assistant", "text": "uh, why do you need my...
{ "chunk_text": "Chunk 1: sure is ni double k i.\nChunk 2: b r o w n n.\nChunk 3: yes, you got it, nikki brown.\nChunk 4: uh, why do you need my email address.\nChunk 5: um sorry, i prefer to give out my email address.\nChunk 6: i'm also looking for a place to go in cambridge.\nChunk 7: uh, yeah, for the location i w...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "sure is ni double k i.", "role": "user", "streaming_reasoning": "The user mentions Sure is ni double k i. It is not yet clear whether the user needs the full scope of th...
{ "answer": "I can help with the attraction. Could you share the type?", "reasoning": "Across the dialogue, the user is searching for place to go in cambridge. Key context: sure is ni double k i; b r o w n n; yes, you got it, nikki brown; uh, why do you need my email address. The answer should focus on the latest u...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1923", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007283
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm rob and he is speaking to robin and i'm looking for some information about a trip in cambridge.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello, how are you.\nChunk 2: i'm rob and he is speaking to robin and i'm looking for some information about a trip in cambridge.", "dialogue_text": "Chunk 1: hello, how are you.\nChunk 2: i'm rob and he is speaking to robin and i'm looking for some information about a trip in cambridge.",...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Hello, how are you. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is searching for information about a trip in cambridge. Key context: hello, how are you; i'm rob and he is speaking to robin and i'm looking for some information about a trip in cambridge. The answer should ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2530", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007284
train
audio
multi_turn
[ { "role": "user", "text": "okay.", "turn_id": 1 }, { "role": "assistant", "text": "i can help at one night.", "turn_id": 2 }, { "role": "user", "text": "d for donald a for alpha insanely i for india e for elephant double l for lima e for elephant last name b for u", "turn...
{ "chunk_text": "Chunk 1: okay.\nChunk 2: i can help at one night.\nChunk 3: d for donald a for alpha insanely i for india e for elephant double l for lima e for elephant last name b for u\nChunk 4: v university s for sugar a for α r for romeo t for turnout\nChunk 5: no, i do mind. i cannot give you my email address....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay.", "role": "user", "streaming_reasoning": "The user mentions Okay. It is not yet clear whether the user needs the full scope of the user's request. The assistant sh...
{ "answer": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: i can help at one night; d for donald a for alpha insanely i for india e for elephant double l for lima e for elephant last name b for u v universi...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3516", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002200
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yes they really catch you, especially the batman begins soundtrack where every track title is named after a bat!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: It is always fun to learn such things like that. It was also fun to know that the tr...
{ "chunk_text": "Chunk 1: Human: Yes they really catch you, especially the batman begins soundtrack where every track title is named after a bat!\nChunk 2: Assistant: It is always fun to learn such things like that. It was also fun to know that the tron legacy soundtrack was negotiated by Daft punk as they wore their...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yes they really catch you, especially the batman begins soundtrack where every track title is named after a bat!", "role": "user", "streaming_reasoning": "The use...
{ "answer": "Maybe they got their clothes and masks from Mars! If not Mars, maybe it's moon that people once thought was made by something or someone.", "reasoning": "Across the dialogue, the user is asking for help with after a bat. Key context: Human: Yes they really catch you, especially the batman begins soundt...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_10d9a046-d4c9-4d62-a069-4a54d650bba4", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002201
train
audio
multi_turn
[ { "role": "user", "text": "Human: ha ya I like the Patriots myself, did you know that Tom Brady came out with a book recently?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I did not. What is it about?", "turn_id": 2 }, { "role": "user", "text": "Human: ya its ...
{ "chunk_text": "Chunk 1: Human: ha ya I like the Patriots myself, did you know that Tom Brady came out with a book recently?\nChunk 2: Assistant: I did not. What is it about?\nChunk 3: Human: ya its all about his tips for success in life, its a best selling \"athelete's bible\"", "dialogue_text": "Chunk 1: Human: ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: ha ya I like the Patriots myself, did you know that Tom Brady came out with a book recently?", "role": "user", "streaming_reasoning": "The user mentions wanting t...
{ "answer": "I will have to look into that. I had no idea. Speaking of the Patriots, did you know that they had a RB who never fumbled a football?!", "reasoning": "Across the dialogue, the user is wanting to book recently. Key context: Human: ha ya I like the Patriots myself, did you know that Tom Brady came out wi...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "fact_lookup" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_6adb3f36-2884-4491-8852-e4f4b99b852e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002202
train
audio
multi_turn
[ { "role": "user", "text": "Human: It is absolutely hilarious. It's got Gene Wilder (the dude who played Willy Wonka). Pretty much a 70s spoof on Western Movies.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Oh its a comedy, then I definitely want to see it. I love comedy and s...
{ "chunk_text": "Chunk 1: Human: It is absolutely hilarious. It's got Gene Wilder (the dude who played Willy Wonka). Pretty much a 70s spoof on Western Movies.\nChunk 2: Assistant: Oh its a comedy, then I definitely want to see it. I love comedy and spoof movies. I also like science fiction. I can't believe some of t...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: It is absolutely hilarious. It's got Gene Wilder (the dude who played Willy Wonka). Pretty much a 70s spoof on Western Movies.", "role": "user", "streaming_reason...
{ "answer": "I agree, I think a lot of people were like closet science fiction fans, but now with all the different events and what not they are more comfortable expressing that. I mean some may take it to far with the whole membership for life that covers you in case you come back", "reasoning": "Across the dialog...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_96578d43-347b-4936-8603-aff6a3421788", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002203
train
audio
multi_turn
[ { "role": "user", "text": "Human: It is funny, but at the same time, maybe it shows that that when Elvis was a kid, music was boring.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: True, I see that he was also a natural blonde, I thought it looked like he had dyed black hair.",...
{ "chunk_text": "Chunk 1: Human: It is funny, but at the same time, maybe it shows that that when Elvis was a kid, music was boring.\nChunk 2: Assistant: True, I see that he was also a natural blonde, I thought it looked like he had dyed black hair.\nChunk 3: Human: that is surprising, today no one who is naturally b...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: It is funny, but at the same time, maybe it shows that that when Elvis was a kid, music was boring.", "role": "user", "streaming_reasoning": "The user mentions ta...
{ "answer": "Lisa Marie Presley, his daughter married both Michael Jackson and Nicolas Cage", "reasoning": "The dialogue is about \"It is funny, but at the same time, maybe it shows that that.\" The user later explains \"that is surprising, today no one who is naturally blonde.\" The answer should treat this as a d...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_6429201d-9adf-434c-b91a-6e5e3ebf8a38", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002204
train
audio
multi_turn
[ { "role": "user", "text": "Human: Talk about a passion project! Probably needed multiple flow charts to keep track of everything....", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah! I was wrong... It was Musk's wife that was in Inception. I have no idea what she looks like....
{ "chunk_text": "Chunk 1: Human: Talk about a passion project! Probably needed multiple flow charts to keep track of everything....\nChunk 2: Assistant: Yeah! I was wrong... It was Musk's wife that was in Inception. I have no idea what she looks like. Nolan got his son in the movie too.\nChunk 3: Human: Aha! I was ju...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Talk about a passion project! Probably needed multiple flow charts to keep track of everything....", "role": "user", "streaming_reasoning": "The user mentions tal...
{ "answer": "Sorry:) I will say Cruise is dedicated. He spent two years learning Japanese for the Last Samurai.", "reasoning": "Across the dialogue, the user is asking for help with to figure out who his wife is. Key context: Human: Talk about a passion project; Probably needed multiple flow charts to keep track of...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_b96704d0-0a7a-4b25-8d11-93d1ead8f229", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007285
train
audio
multi_turn
[ { "role": "user", "text": "i will leave after 1630.", "turn_id": 1 }, { "role": "assistant", "text": "yes, you're right.", "turn_id": 2 }, { "role": "user", "text": "yes, it's kinkling.", "turn_id": 3 }, { "role": "assistant", "text": "okay, thank you.", "...
{ "chunk_text": "Chunk 1: i will leave after 1630.\nChunk 2: yes, you're right.\nChunk 3: yes, it's kinkling.\nChunk 4: okay, thank you.\nChunk 5: okay. can you tell me the earliest one.\nChunk 6: okay. can you repeat it.\nChunk 7: okay, that's great. and.\nChunk 8: no, that's all. thank you.", "dialogue_text": "Ch...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i will leave after 1630.", "role": "user", "streaming_reasoning": "The user mentions I will leave after 1630. It is not yet clear whether the user needs the full scope o...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is talking about i will leave after 1630. Key context: i will leave after 1630; yes, you're right; yes, it's kinkling; okay, thank you. The answer should focus on the latest user tu...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0010", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007286
train
audio
multi_turn
[ { "role": "user", "text": "okay, great.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm also looking for twin service.", "turn_id": 2 }, { "role": "user", "text": "i'm departing from cambridge and heading to london liverpool street.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: okay, great.\nChunk 2: yes, i'm also looking for twin service.\nChunk 3: i'm departing from cambridge and heading to london liverpool street.\nChunk 4: okay, i'm living on friday. and i'm targeting to arrive by 3 15 pm.\nChunk 5: yes, thank you.\nChunk 6: alright, um. may i have the train id...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, great.", "role": "user", "streaming_reasoning": "The user mentions Okay, great. It is not yet clear whether the user needs the full scope of the user's request. Th...
{ "answer": "Sure. I can provide the id, leaveat for the matching train option.", "reasoning": "Across the dialogue, the user is searching for twin service. Key context: okay, great; yes, i'm also looking for twin service; i'm departing from cambridge and heading to london liverpool street; okay, i'm living on frid...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3446", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007287
train
audio
multi_turn
[ { "role": "user", "text": "okay.", "turn_id": 1 }, { "role": "assistant", "text": "okay, perfect.", "turn_id": 2 }, { "role": "user", "text": "yes. and also. to a bucket table for four people at 8 o'clock on sunday.", "turn_id": 3 }, { "role": "assistant", "te...
{ "chunk_text": "Chunk 1: okay.\nChunk 2: okay, perfect.\nChunk 3: yes. and also. to a bucket table for four people at 8 o'clock on sunday.\nChunk 4: okay. how about 7 o'clock.\nChunk 5: m for mother i for india c for charlie h for hanna e for elephant double l for lima e for elephant last name a\nChunk 6: w for wend...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay.", "role": "user", "streaming_reasoning": "The user mentions Okay. It is not yet clear whether the user needs the full scope of the user's request. The assistant sh...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is talking about okay, perfect. Key context: okay, perfect; to a bucket table for four people at 8 o'clock on sunday; how about 7 o'clock; m for mother i for india c for charlie h for hanna e fo...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1205", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007288
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is james. i need your help with the phone number.", "turn_id": 1 }, { "role": "assistant", "text": "um i need to contact a specialist department in the hospital.", "turn_id": 2 }, { "role": "user", "text": "um it's a brain federal depart...
{ "chunk_text": "Chunk 1: hi, my name is james. i need your help with the phone number.\nChunk 2: um i need to contact a specialist department in the hospital.\nChunk 3: um it's a brain federal department.\nChunk 4: okay. yes, that's the one. can i please have the phone number.\nChunk 5: okay.\nChunk 6: yes, thank yo...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is james. i need your help with the phone number.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is james. It is not yet clear wheth...
{ "answer": "Sure. I can provide the phone for the matching hospital option.", "reasoning": "Across the dialogue, the user is talking about your help with the phone number. Key context: hi, my name is james; i need your help with the phone number; um i need to contact a specialist department in the hospital; um it'...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0574", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002205
train
audio
multi_turn
[ { "role": "user", "text": "Human: It is funny how Iowas locker room for visitors in painted in all pink!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I heard about that! College stadiums are no joke. Fourteen of the world's largest 25 stadiums belong to American college footb...
{ "chunk_text": "Chunk 1: Human: It is funny how Iowas locker room for visitors in painted in all pink!\nChunk 2: Assistant: I heard about that! College stadiums are no joke. Fourteen of the world's largest 25 stadiums belong to American college football teams!\nChunk 3: Human: That is wild. The highest score of a fo...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: It is funny how Iowas locker room for visitors in painted in all pink!", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Iowas. It ...
{ "answer": "No way. A Snoop Dogg song just came on the radio, and it reminded me that he once wrote a fight song for his son's high school football team! I don't think I've ever heard that one over the radio waves!", "reasoning": "Across the dialogue, the user discusses \"It is funny how Iowas locker room for visi...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_fd00ca19-25b0-4f63-a47a-0b6b1722d79a", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007289
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes. so i am looking for a place to stay. were you able to help me.", "turn_id": 2 }, { "role": "user", "text": "so i am looking for a hotel in the center area that, uh, i prefer to including ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes. so i am looking for a place to stay. were you able to help me.\nChunk 3: so i am looking for a hotel in the center area that, uh, i prefer to including free wi fi. is there any hotel like.\nChunk 4: yes. and i also want to, uh, see that whether, uh, i wanted to find any...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help book that. Could you provide the price, hotel_type, day?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: so i am looking for a place to stay; were you able to help me; so i am looking for a hotel in the center area that, uh, i prefer to including fr...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0803", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007290
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you. hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm awesome thank you um i would like to book a table in the restaurant that that's in the western side of cambridge and it", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: hello, how are you. hello, how are you.\nChunk 2: i'm awesome thank you um i would like to book a table in the restaurant that that's in the western side of cambridge and it\nChunk 3: should be in the expensive price range and and it's it must serve korean foot\nChunk 4: okay. how about the ...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, how are you. hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Hello, how are you. hello, how are you. It is not yet clear whether t...
{ "answer": "I can help book that. Could you provide the day, time, party_size?", "reasoning": "Across the dialogue, the user is wanting to book table in the restaurant that that's in the western side of cambridge. Key context: hello, how are you; hello, how are you; how about the one that sells european food. The ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1265", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007291
train
audio
multi_turn
[ { "role": "user", "text": "hi. is that customer service center.", "turn_id": 1 }, { "role": "assistant", "text": "a pretty good thanks for asking and you.", "turn_id": 2 }, { "role": "user", "text": "uh, yes, i'm i'm looking for taxi booking. can you help me to book.", "t...
{ "chunk_text": "Chunk 1: hi. is that customer service center.\nChunk 2: a pretty good thanks for asking and you.\nChunk 3: uh, yes, i'm i'm looking for taxi booking. can you help me to book.\nChunk 4: oh, i'm gonna leave hk fusion.\nChunk 5: uh, my friends waiting me in british guest house. i'm gonna go there.\nChun...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi. is that customer service center.", "role": "user", "streaming_reasoning": "The user mentions Hi. is that customer service center. It is not yet clear whether the use...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for taxi booking. Key context: is that customer service center; a pretty good thanks for asking and you; uh, yes, i'm i'm looking for taxi booking; ca...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0700", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007292
train
audio
multi_turn
[ { "role": "user", "text": "hi, i'm looking to get some information.", "turn_id": 1 }, { "role": "assistant", "text": "looking to and attend possibly a show while i'm in cambridge.", "turn_id": 2 }, { "role": "user", "text": "okay. what area is that located in.", "turn_id"...
{ "chunk_text": "Chunk 1: hi, i'm looking to get some information.\nChunk 2: looking to and attend possibly a show while i'm in cambridge.\nChunk 3: okay. what area is that located in.\nChunk 4: do you have the post code.\nChunk 5: and is there an entrance fee? do you know for that.\nChunk 6: okay. um i also need som...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, i'm looking to get some information.", "role": "user", "streaming_reasoning": "The user mentions Hi, i'm looking to get some information. It is not yet clear whether...
{ "answer": "I can help with the restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user discusses \"hi, i'm looking to get some.\" over 6 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Acr...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2363", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007293
train
audio
multi_turn
[ { "role": "user", "text": "hello, can you hear me.", "turn_id": 1 }, { "role": "assistant", "text": "uh is that customer service.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "i will lea...
{ "chunk_text": "Chunk 1: hello, can you hear me.\nChunk 2: uh is that customer service.\nChunk 3: i'm looking for a train.\nChunk 4: i will leave on monday, you know.\nChunk 5: yes. and i will leave after fifteen forty five, please.\nChunk 6: yes. and i will depart from a name, a place named c. e. m. b. or something...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, can you hear me.", "role": "user", "streaming_reasoning": "The user mentions Hello, can you hear me. It is not yet clear whether the user needs the full scope of ...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: hello, can you hear me; uh is that customer service; i'm looking for a train; i will leave on monday, you know. The answer should focus on the latest user turn ...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3925", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002206
train
audio
multi_turn
[ { "role": "user", "text": "Human: Ohh that is pretty cool. The sun is still on bilionth of the biggest star in the galaxy", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Wow that really puts things into perspective. Do you by any chance like animals?", "turn_id": 2 }, { ...
{ "chunk_text": "Chunk 1: Human: Ohh that is pretty cool. The sun is still on bilionth of the biggest star in the galaxy\nChunk 2: Assistant: Wow that really puts things into perspective. Do you by any chance like animals?\nChunk 3: Human: I do. I have a cat and two dogs. How about you?", "dialogue_text": "Chunk 1:...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Ohh that is pretty cool. The sun is still on bilionth of the biggest star in the galaxy", "role": "user", "streaming_reasoning": "The user mentions talking about ...
{ "answer": "I have a dog only but I also like horses. When they leave Iceland they are not allowed to return there", "reasoning": "Across the dialogue, the user discusses \"Ohh that is pretty cool. The sun is still on bilionth of.\" over 3 turns. The answer should respond to the latest user turn naturally, maintai...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_0fd70cb7-4cb2-45c9-b976-12e9891d2d83", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007294
train
audio
multi_turn
[ { "role": "user", "text": "yes. uh, can i please get the price.", "turn_id": 1 }, { "role": "assistant", "text": "£13 and 20. thank you very much, ma'am.", "turn_id": 2 }, { "role": "user", "text": "what about the arrival of time, ma'am.", "turn_id": 3 }, { "role"...
{ "chunk_text": "Chunk 1: yes. uh, can i please get the price.\nChunk 2: £13 and 20. thank you very much, ma'am.\nChunk 3: what about the arrival of time, ma'am.\nChunk 4: 1327. okay, that's great, man. thank you.\nChunk 5: yes, ma'am. i'm also looking for places to go in town.\nChunk 6: the italian should be in the ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes. uh, can i please get the price.", "role": "user", "streaming_reasoning": "The user mentions Yes. uh, can i please get the price. It is not yet clear whether the use...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for places to go in town. Key context: uh, can i please get the price; thank you very much, ma'am; what about the arrival of time, ma'am; okay, that's great, man. The answer should focus...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2612", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002207
train
audio
multi_turn
[ { "role": "user", "text": "Human: Not a die-hard fan but I keep up with it. What about you? I have some trivia about football if you're interested.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I'm about the same. Sure, I'd like to hear it.", "turn_id": 2 }, { "rol...
{ "chunk_text": "Chunk 1: Human: Not a die-hard fan but I keep up with it. What about you? I have some trivia about football if you're interested.\nChunk 2: Assistant: I'm about the same. Sure, I'd like to hear it.\nChunk 3: Human: Do you know about the tracking chips the NFL uses during the game?", "dialogue_text"...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Not a die-hard fan but I keep up with it. What about you? I have some trivia about football if you're interested.", "role": "user", "streaming_reasoning": "The us...
{ "answer": "I have heard a little, I'm surprised they are able to use it during the game and not just practice.", "reasoning": "Across the dialogue, the user discusses \"Not a die-hard fan but I keep up with it. What about you? I.\" over 3 turns. The answer should respond to the latest user turn naturally, maintai...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_4afb256e-d054-44d8-a100-3902a556984d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007295
train
audio
multi_turn
[ { "role": "user", "text": "uh, why do you need my email address.", "turn_id": 1 }, { "role": "assistant", "text": "uh, sorry, i prefer to give up my email address.", "turn_id": 2 }, { "role": "user", "text": "i am also looking for a place to go in cambridge.", "turn_id": ...
{ "chunk_text": "Chunk 1: uh, why do you need my email address.\nChunk 2: uh, sorry, i prefer to give up my email address.\nChunk 3: i am also looking for a place to go in cambridge.\nChunk 4: um, i i i want to visit a college in cambridge.\nChunk 5: uh, i'll go with claire college, please.\nChunk 6: mm. yes, i want ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, why do you need my email address.", "role": "user", "streaming_reasoning": "The user mentions Uh, why do you need my email address. It is not yet clear whether the u...
{ "answer": "Sure. I can provide the area, fee for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for place to go in cambridge. Key context: uh, why do you need my email address; uh, sorry, i prefer to give up my email address; i am also looking for a place to go in cambr...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1913", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002208
train
audio
multi_turn
[ { "role": "user", "text": "Human: Are you a baseball fan? I'm not, so I am not surprised that the Women's World cup has higher ratings than the World Series.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Soccer is the international sport. Women around the world will be keen on...
{ "chunk_text": "Chunk 1: Human: Are you a baseball fan? I'm not, so I am not surprised that the Women's World cup has higher ratings than the World Series.\nChunk 2: Assistant: Soccer is the international sport. Women around the world will be keen on seeing the games. Not so much for baseball, I guess. I am not a bi...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Are you a baseball fan? I'm not, so I am not surprised that the Women's World cup has higher ratings than the World Series.", "role": "user", "streaming_reasoning...
{ "answer": "Chess is a very old game. The term \"checkmate\" means something about the king dying.", "reasoning": "Across the dialogue, the user is asking for help with human: are you a baseball fan. Key context: Human: Are you a baseball fan; I'm not, so I am not surprised that the Women's World cup has higher ra...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_cafe82d2-ca62-4889-8b7c-67cdd712685f", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007296
train
audio
multi_turn
[ { "role": "user", "text": "hi.", "turn_id": 1 }, { "role": "assistant", "text": "oh, i want to eat in the downtown of this city. please help me find a restaurant.", "turn_id": 2 }, { "role": "user", "text": "i prefer some turkish food. in a cheap price, please.", "turn_id...
{ "chunk_text": "Chunk 1: hi.\nChunk 2: oh, i want to eat in the downtown of this city. please help me find a restaurant.\nChunk 3: i prefer some turkish food. in a cheap price, please.\nChunk 4: i prefer turkish food in a cheap price.\nChunk 5: and then how about some. spanish food with. ya.", "dialogue_text": "Ch...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi.", "role": "user", "streaming_reasoning": "The user mentions Hi. It is not yet clear whether the user needs the full scope of the user's request. The assistant should...
{ "answer": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user discusses \"hi.\" over 5 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user disc...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0016", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007297
train
audio
multi_turn
[ { "role": "user", "text": "yes.", "turn_id": 1 }, { "role": "assistant", "text": "cambodia sounds good. can you tell me when does it open.", "turn_id": 2 }, { "role": "user", "text": "okay. and do i need to pay for the ticket.", "turn_id": 3 }, { "role": "assistan...
{ "chunk_text": "Chunk 1: yes.\nChunk 2: cambodia sounds good. can you tell me when does it open.\nChunk 3: okay. and do i need to pay for the ticket.\nChunk 4: okay i got that and the i also want to find a hotel with a star of four maybe uh maybe with a an expensive price\nChunk 5: okay.\nChunk 6: and.\nChunk 7: oka...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes.", "role": "user", "streaming_reasoning": "The user mentions Yes. It is not yet clear whether the user needs the full scope of the user's request. The assistant shou...
{ "answer": "I can help with the hotel. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for to pay for the ticket. Key context: cambodia sounds good; can you tell me when does it open; and do i need to pay for the ticket; okay i got that and the i also want to find a hotel with ...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1244", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002209
train
audio
multi_turn
[ { "role": "user", "text": "Human: Wow. Judit Polgar was so good at it that he beat a family friend at the game when he was 5 and did not even look at the board", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That is seriously impressive. I am just happy to know how the pieces mo...
{ "chunk_text": "Chunk 1: Human: Wow. Judit Polgar was so good at it that he beat a family friend at the game when he was 5 and did not even look at the board\nChunk 2: Assistant: That is seriously impressive. I am just happy to know how the pieces move - and that a knight can visit each square exactly once\nChunk 3:...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Wow. Judit Polgar was so good at it that he beat a family friend at the game when he was 5 and did not even look at the board", "role": "user", "streaming_reasoni...
{ "answer": "Really? I would have thought you needed to be pretty smart to play chess! But maybe not since pawns no longer have their own names like they used to", "reasoning": "Across the dialogue, the user is asking for help with judit polgar was so good at it that he beat a family friend at the game when he was ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_884defa9-a093-4ef3-9afb-e3af33450069", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007298
train
audio
multi_turn
[ { "role": "user", "text": "and more thank you as speaking to dora mindy and i'm looking for some information. about the tripping courage.", "turn_id": 1 }, { "role": "assistant", "text": "so i'm looking for places to go to in town. the attraction should be a swimming pool and it should be in...
{ "chunk_text": "Chunk 1: and more thank you as speaking to dora mindy and i'm looking for some information. about the tripping courage.\nChunk 2: so i'm looking for places to go to in town. the attraction should be a swimming pool and it should be in the north.\nChunk 3: no problem.\nChunk 4: mm. okay.\nChunk 5: let...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and more thank you as speaking to dora mindy and i'm looking for some information. about the tripping courage.", "role": "user", "streaming_reasoning": "The user mention...
{ "answer": "Sure. I can provide the phone, fee for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for information. Key context: and more thank you as speaking to dora mindy and i'm looking for some information; about the tripping courage; so i'm looking for places to go ...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0976", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007299
train
audio
multi_turn
[ { "role": "user", "text": "hello hello. hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i'm planning a trip to cambridge. i'm looking for places to go in town. in particular, i'm looking for one of your wonderful colleges.", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: hello hello. hello. hello.\nChunk 2: hi, i'm planning a trip to cambridge. i'm looking for places to go in town. in particular, i'm looking for one of your wonderful colleges.\nChunk 3: yes, i know of it. i would like to see it indeed. could i get the address, please.\nChunk 4: that's great....
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello hello. hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello hello. hello. hello. It is not yet clear whether the user needs the full sco...
{ "answer": "Sure. I can provide the postcode, phone for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for places to go in town. Key context: hello hello; hi, i'm planning a trip to cambridge; i'm looking for places to go in town; in particular, i'm looking for one of yo...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2911", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007300
train
audio
multi_turn
[ { "role": "user", "text": "at a restaurant. for five.", "turn_id": 1 }, { "role": "assistant", "text": "yes.", "turn_id": 2 }, { "role": "user", "text": "gotta talk great.", "turn_id": 3 }, { "role": "assistant", "text": "my name is joseph willie.", "turn_...
{ "chunk_text": "Chunk 1: at a restaurant. for five.\nChunk 2: yes.\nChunk 3: gotta talk great.\nChunk 4: my name is joseph willie.\nChunk 5: my name is j o f.\nChunk 6: ep h.\nChunk 7: and my same name is w i l ey.\nChunk 8: yes, please. i'm also looking for a train.", "dialogue_text": "Chunk 1: at a restaurant. f...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "at a restaurant. for five.", "role": "user", "streaming_reasoning": "The user mentions At a restaurant. for five. It is not yet clear whether the user needs the timing a...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for train. Key context: at a restaurant; gotta talk great; my name is joseph willie; my name is j o f. The answer should focus on the latest user turn while incorporati...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3577", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007301
train
audio
multi_turn
[ { "role": "user", "text": "sure. may you may i know the more details.", "turn_id": 1 }, { "role": "assistant", "text": "okay, it sounds good.", "turn_id": 2 }, { "role": "user", "text": "well, it's also acceptable.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: sure. may you may i know the more details.\nChunk 2: okay, it sounds good.\nChunk 3: well, it's also acceptable.\nChunk 4: yes. uh, i prefer the festival. may i know more detail information.\nChunk 5: well, may i know the phone number of the first hotel.\nChunk 6: okay, thank you so much. an...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "sure. may you may i know the more details.", "role": "user", "streaming_reasoning": "The user mentions Sure. may you may i know the more details. It is not yet clear whe...
{ "answer": "I can help with the train. Could you share the destination, day, time?", "reasoning": "Across the dialogue, the user is searching for trend. Key context: may you may i know the more details; okay, it sounds good; well, it's also acceptable; uh, i prefer the festival. The answer should focus on the late...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1139", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002210
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah. I guess so. DO you know where the game was invented?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: India I believe - and it became more modern in Spain in the 1400s", "turn_id": 2 }, { "role": "user", "text": "Human: Yes ...
{ "chunk_text": "Chunk 1: Human: Yeah. I guess so. DO you know where the game was invented?\nChunk 2: Assistant: India I believe - and it became more modern in Spain in the 1400s\nChunk 3: Human: Yes it was India during the Gupta Empire and it was improved by the Persians later", "dialogue_text": "Chunk 1: Human: Y...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah. I guess so. DO you know where the game was invented?", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Yeah. It is not yet cl...
{ "answer": "The rules however were not standardized until the 19th century", "reasoning": "Across the dialogue, the user discusses \"Yeah. I guess so. DO you know where the game was.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "R...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_884defa9-a093-4ef3-9afb-e3af33450069", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007302
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you. hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "well thank you my name is kim and i'm if i tell about it but i'm going to take to cambridge i don't know if", "turn_id": 2 }, { "role": "user", "text": "you ca...
{ "chunk_text": "Chunk 1: hello, how are you. hello, how are you.\nChunk 2: well thank you my name is kim and i'm if i tell about it but i'm going to take to cambridge i don't know if\nChunk 3: you can assist me some information\nChunk 4: okay so firstly i'm looking for a place to stay the hotel should be a zero star...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, how are you. hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Hello, how are you. hello, how are you. It is not yet clear whether t...
{ "answer": "I can help book that. Could you provide the price, day, stay_length?", "reasoning": "Across the dialogue, the user is searching for place to stay the hotel should be a zero star. Key context: hello, how are you; hello, how are you; okay, that would be fun; can you book it for. The answer should focus o...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1577", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002211
train
audio
multi_turn
[ { "role": "user", "text": "Human: yeah, apparently they put chips in their shoulder pads!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Do you like basketball? I like the smaller team of 5 as opposed to the larger football teams.", "turn_id": 2 }, { "role": "user",...
{ "chunk_text": "Chunk 1: Human: yeah, apparently they put chips in their shoulder pads!\nChunk 2: Assistant: Do you like basketball? I like the smaller team of 5 as opposed to the larger football teams.\nChunk 3: Human: I watch it sometimes. They banned the dunk for awhile because Kareem.", "dialogue_text": "Chunk...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: yeah, apparently they put chips in their shoulder pads!", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not yet clear wheth...
{ "answer": "What did Kareem do? Did he play for Kansas where james naissmith was a losing coach?", "reasoning": "Across the dialogue, the user discusses \"yeah, apparently they put chips in their shoulder.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational t...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_d9abed6c-46d6-401c-a307-2e0f699868a2", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007303
train
audio
multi_turn
[ { "role": "user", "text": "ya, that's right on monday.", "turn_id": 1 }, { "role": "assistant", "text": "that's correct.", "turn_id": 2 }, { "role": "user", "text": "ya, that's right.", "turn_id": 3 }, { "role": "assistant", "text": "is the earliest one.", ...
{ "chunk_text": "Chunk 1: ya, that's right on monday.\nChunk 2: that's correct.\nChunk 3: ya, that's right.\nChunk 4: is the earliest one.\nChunk 5: ya.\nChunk 6: okay. ya, uh, my id number is 6 8 2 2.\nChunk 7: 7 6 0 9.\nChunk 8: 3, 1, 5, 6.", "dialogue_text": "Chunk 1: ya, that's right on monday.\nChunk 2: that's...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "ya, that's right on monday.", "role": "user", "streaming_reasoning": "The user mentions Ya, that's right on monday. It is not yet clear whether the user needs the full s...
{ "answer": "I can help with the train. Could you share the departure?", "reasoning": "Across the dialogue, the user is talking about ya, that's right on monday. Key context: ya, that's right on monday; that's correct; ya, that's right; is the earliest one. The answer should focus on the latest user turn while inco...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3260", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007304
train
audio
multi_turn
[ { "role": "user", "text": "so i prefer it in the cheap price range and located in the west.", "turn_id": 1 }, { "role": "assistant", "text": "and also i want it has a store for and include free wi fi.", "turn_id": 2 }, { "role": "user", "text": "ya. uh, well, that is for.", ...
{ "chunk_text": "Chunk 1: so i prefer it in the cheap price range and located in the west.\nChunk 2: and also i want it has a store for and include free wi fi.\nChunk 3: ya. uh, well, that is for.\nChunk 4: fingertips bed and breakfast sounds great. can you book me for like four people.\nChunk 5: i will be there star...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "so i prefer it in the cheap price range and located in the west.", "role": "user", "streaming_reasoning": "The user mentions So i prefer it in the cheap price range and ...
{ "answer": "I can help book that. Could you provide the hotel_type?", "reasoning": "Across the dialogue, the user is searching for me for like four people. Key context: so i prefer it in the cheap price range and located in the west; and also i want it has a store for and include free wi fi; uh, well, that is for;...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1807", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007305
train
audio
multi_turn
[ { "role": "user", "text": "i'm great. and can you please book me a ticket to commute me from saladan to the neurology.", "turn_id": 1 }, { "role": "assistant", "text": "um it should depart after 3:45 in the morning.", "turn_id": 2 }, { "role": "user", "text": "yes, please. it...
{ "chunk_text": "Chunk 1: i'm great. and can you please book me a ticket to commute me from saladan to the neurology.\nChunk 2: um it should depart after 3:45 in the morning.\nChunk 3: yes, please. it's 1 8. so did you get that.\nChunk 4: 4 2 6 did you get that.\nChunk 5: and lastly, it's 9 9 total.\nChunk 6: alright...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm great. and can you please book me a ticket to commute me from saladan to the neurology.", "role": "user", "streaming_reasoning": "The user mentions I'm great. It is ...
{ "answer": "Sure. I can provide the car for the matching taxi option.", "reasoning": "Across the dialogue, the user is wanting to book me a ticket to commute me from saladan to the neurology. Key context: and can you please book me a ticket to commute me from saladan to the neurology; um it should depart after 3:4...
{ "category": "finance_consumer", "subcategory": "budget_planning", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0547", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007306
train
audio
multi_turn
[ { "role": "user", "text": "i should leave after 20 o'clock.", "turn_id": 1 }, { "role": "assistant", "text": "and it should leave on wednesday.", "turn_id": 2 }, { "role": "user", "text": "yes, and to depart from bishop stafford.", "turn_id": 3 }, { "role": "assis...
{ "chunk_text": "Chunk 1: i should leave after 20 o'clock.\nChunk 2: and it should leave on wednesday.\nChunk 3: yes, and to depart from bishop stafford.\nChunk 4: yes, and should go to cambridge.\nChunk 5: yes, that's all my comments.\nChunk 6: okay, thank you.\nChunk 7: okay. um, please, uh, uh, please recommend fo...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i should leave after 20 o'clock.", "role": "user", "streaming_reasoning": "The user mentions I should leave after 20 o'clock. It is not yet clear whether the user needs ...
{ "answer": "Sure. I can provide the ticket, id, travel_time for the matching train option.", "reasoning": "Across the dialogue, the user is asking for recommendations about to get the price. Key context: i should leave after 20 o'clock; and it should leave on wednesday; yes, and to depart from bishop stafford; yes...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3930", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007307
train
audio
multi_turn
[ { "role": "user", "text": "yes.", "turn_id": 1 }, { "role": "assistant", "text": "yes, correct.", "turn_id": 2 }, { "role": "user", "text": "yes.", "turn_id": 3 }, { "role": "assistant", "text": "okay, i will book it.", "turn_id": 4 }, { "role": "u...
{ "chunk_text": "Chunk 1: yes.\nChunk 2: yes, correct.\nChunk 3: yes.\nChunk 4: okay, i will book it.\nChunk 5: and six people.\nChunk 6: okay, i remember at 7 6. 7 3 7 8 2 4 8 5.\nChunk 7: 6, 7, 6, 6.\nChunk 8: 5, 4.", "dialogue_text": "Chunk 1: yes.\nChunk 2: yes, correct.\nChunk 3: yes.\nChunk 4: okay, i will bo...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes.", "role": "user", "streaming_reasoning": "The user mentions Yes. It is not yet clear whether the user needs the full scope of the user's request. The assistant shou...
{ "answer": "I can help book that. Could you provide the departure, destination, day?", "reasoning": "Across the dialogue, the user is wanting to book yes, correct. Key context: yes, correct; okay, i will book it; and six people; okay, i remember at 7 6. The answer should focus on the latest user turn while incorpo...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1806", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007308
train
audio
multi_turn
[ { "role": "user", "text": "okay, i'll do with it.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i want i want to put it for me. and four friends. over two nights starting from wednesday.", "turn_id": 2 }, { "role": "user", "text": "my name is dean flory.", "turn_...
{ "chunk_text": "Chunk 1: okay, i'll do with it.\nChunk 2: yes, i want i want to put it for me. and four friends. over two nights starting from wednesday.\nChunk 3: my name is dean flory.\nChunk 4: the parade members as.\nChunk 5: 7, 8.\nChunk 6: wl i.\nChunk 7: no, nothing else, ma'am.\nChunk 8: no, i'm not typing t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, i'll do with it.", "role": "user", "streaming_reasoning": "The user mentions Okay, i'll do with it. It is not yet clear whether the user needs the full scope of th...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is talking about i want to put it for me. Key context: okay, i'll do with it; yes, i want i want to put it for me; and four friends; over two nights starting from wednesday. The answer should focu...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2310", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007309
train
audio
multi_turn
[ { "role": "user", "text": "okay, great. and also i'm looking for a place to stay and i do not need the internet, but i need the free parking.", "turn_id": 1 }, { "role": "assistant", "text": "yeah.", "turn_id": 2 }, { "role": "user", "text": "yes, right.", "turn_id": 3 ...
{ "chunk_text": "Chunk 1: okay, great. and also i'm looking for a place to stay and i do not need the internet, but i need the free parking.\nChunk 2: yeah.\nChunk 3: yes, right.\nChunk 4: um alright, also. um can you find me 1? have a star of 4 and i'd like to, um, get a gift hub.\nChunk 5: okay.\nChunk 6: um okay, ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, great. and also i'm looking for a place to stay and i do not need the internet, but i need the free parking.", "role": "user", "streaming_reasoning": "The user men...
{ "answer": "Sure. I can provide the phone for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: okay, great; and also i'm looking for a place to stay and i do not need the internet, but i need the free parking; um alright, also; um can you find me...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0212", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007310
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i'm traveling to cambridge and i am looking forward to try local restaurants.", "turn_id": 2 }, { "role": "user", "text": "i would like a place to stay.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi, i'm traveling to cambridge and i am looking forward to try local restaurants.\nChunk 3: i would like a place to stay.", "dialogue_text": "Chunk 1: hello.\nChunk 2: hi, i'm traveling to cambridge and i am looking forward to try local restaurants.\nChunk 3: i would like ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: hi, i'm traveling to cambridge and i am looking forward to try local restaurants; i would like a place to stay. The answer should focus on t...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3082", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002212
train
audio
multi_turn
[ { "role": "user", "text": "Human: that's a good question, we will have to see, I want to see the AI that can identify classical music just from vinyl records like Arthur Lintgen apparently can", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That is unbelievable! I would find it ...
{ "chunk_text": "Chunk 1: Human: that's a good question, we will have to see, I want to see the AI that can identify classical music just from vinyl records like Arthur Lintgen apparently can\nChunk 2: Assistant: That is unbelievable! I would find it hard to believe that AI could accomplish a feat such as turning Sil...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: that's a good question, we will have to see, I want to see the AI that can identify classical music just from vinyl records like Arthur Lintgen apparently can", "role":...
{ "answer": "I will look that up. Why do you think that Silent Night composers wanted to commemorate Armistice Day that occurred more than a century ago?", "reasoning": "Across the dialogue, the user is searching for they will not grow old. Key context: Human: that's a good question, we will have to see, I want to ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_35d7f32a-7183-4636-913f-61f665de4e0b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007311
train
audio
multi_turn
[ { "role": "user", "text": "for that, um, may i know the train id.", "turn_id": 1 }, { "role": "assistant", "text": "okay, got that. thank you very much.", "turn_id": 2 }, { "role": "user", "text": "um yes, i'm also looking for a place to stay.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: for that, um, may i know the train id.\nChunk 2: okay, got that. thank you very much.\nChunk 3: um yes, i'm also looking for a place to stay.\nChunk 4: well, it should be in the type of guest house.\nChunk 5: uh, what's more. the hotel should include free wi fi.\nChunk 6: that's right. and h...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "for that, um, may i know the train id.", "role": "user", "streaming_reasoning": "The user mentions For that, um, may i know the train id. It is not yet clear whether the...
{ "answer": "I can help with the hotel. Could you share the area, price?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: for that, um, may i know the train id; okay, got that; thank you very much; um yes, i'm also looking for a place to stay. The answer should focus on the...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1147", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002213
train
audio
multi_turn
[ { "role": "user", "text": "Human: That's great! There should a team entirely of women!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That would be interesting to watch! With only 11 minutes of live game play on average, gives time to eat footall treats or standing in line at t...
{ "chunk_text": "Chunk 1: Human: That's great! There should a team entirely of women!\nChunk 2: Assistant: That would be interesting to watch! With only 11 minutes of live game play on average, gives time to eat footall treats or standing in line at the stadium. lol\nChunk 3: Human: I figure the best way to watch the...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: That's great! There should a team entirely of women!", "role": "user", "streaming_reasoning": "The user mentions Human: That's great! There should a team entirely...
{ "answer": "That is surprising. Makes sense with the average player. Do you watch the New Orleans Saints?", "reasoning": "Across the dialogue, the user is asking for help with human: that's great. Key context: Human: That's great; There should a team entirely of women; Assistant: That would be interesting to watch...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_b5917861-1d15-4ddf-8b81-c22b2361adb7", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002214
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yes he is, he is a wide receiver. And he normally works well with the quarterback Kyle lauletta, they play at the Cole Field House by the way", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Wow. I think it is great that there are a bunch of good...
{ "chunk_text": "Chunk 1: Human: Yes he is, he is a wide receiver. And he normally works well with the quarterback Kyle lauletta, they play at the Cole Field House by the way\nChunk 2: Assistant: Wow. I think it is great that there are a bunch of good up and coming players.\nChunk 3: Human: Yes I agree, they definite...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yes he is, he is a wide receiver. And he normally works well with the quarterback Kyle lauletta, they play at the Cole Field House by the way", "role": "user", "s...
{ "answer": "I dont watch too much, there is only 11 minutes of live action. I dont have time to spend 3 hours watching a game for 11 minutes.", "reasoning": "Across the dialogue, the user is asking for help with human: yes he is, he is a wide receiver. Key context: Human: Yes he is, he is a wide receiver; And he n...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_a4b7099d-f0a4-4a83-8003-b145466758b5", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007312
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi i'm traveling to cambridge and i want to see some local tourist attractions there's a one named the cherry hinton village center can you", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi i'm traveling to cambridge and i want to see some local tourist attractions there's a one named the cherry hinton village center can you", "dialogue_text": "Chunk 1: hello.\nChunk 2: hi i'm traveling to cambridge and i want to see some local tourist attractions there's ...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the attraction. Could you share the area, type?", "reasoning": "Across the dialogue, the user discusses \"hello.\" over 2 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user di...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0553", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007313
train
audio
multi_turn
[ { "role": "user", "text": "good day.", "turn_id": 1 }, { "role": "assistant", "text": "um yes. can you please assist me in looking for a restaurant.", "turn_id": 2 }, { "role": "user", "text": "yes. um, it should be in the central area and be in the expensive price range and ...
{ "chunk_text": "Chunk 1: good day.\nChunk 2: um yes. can you please assist me in looking for a restaurant.\nChunk 3: yes. um, it should be in the central area and be in the expensive price range and also serves some vietnamese food.\nChunk 4: okay. could you please look for one that serves korean food instead of.\nC...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "good day.", "role": "user", "streaming_reasoning": "The user mentions Good day. It is not yet clear whether the user needs the full scope of the user's request. The assi...
{ "answer": "I can help book that. Could you provide the day, time?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: can you please assist me in looking for a restaurant; um, it should be in the central area and be in the expensive price range and also serves some vietnamese f...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0929", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002215
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yes I agree that tends to be how most shows go. I really like movies from the bromantic comedy genre like The Hangover. Zach Galifinakis is my favorite!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: He is so funny. I like step brothers too!", ...
{ "chunk_text": "Chunk 1: Human: Yes I agree that tends to be how most shows go. I really like movies from the bromantic comedy genre like The Hangover. Zach Galifinakis is my favorite!\nChunk 2: Assistant: He is so funny. I like step brothers too!\nChunk 3: Human: Oh man that is one of my all time favorites!! Bill M...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yes I agree that tends to be how most shows go. I really like movies from the bromantic comedy genre like The Hangover. Zach Galifinakis is my favorite!", "role": "user...
{ "answer": "I think so but who knows! He is a little ecsentric!", "reasoning": "Across the dialogue, the user is asking for help with human: yes i agree that tends to be how most shows go. Key context: Human: Yes I agree that tends to be how most shows go; I really like movies from the bromantic comedy genre like ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_12ff81fd-4064-4369-a501-30bcb48b9f49", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007314
train
audio
multi_turn
[ { "role": "user", "text": "yes, i would like to make a reservation with.", "turn_id": 1 }, { "role": "assistant", "text": "i also have a book.", "turn_id": 2 }, { "role": "user", "text": "on her husband.", "turn_id": 3 }, { "role": "assistant", "text": "uh, ac...
{ "chunk_text": "Chunk 1: yes, i would like to make a reservation with.\nChunk 2: i also have a book.\nChunk 3: on her husband.\nChunk 4: uh, acs canalis.\nChunk 5: ok, thanks very much.\nChunk 6: yes, ma'am, i am also looking for a particular piece of.\nChunk 7: uh, the name of trust called the.\nChunk 8: uh, the fu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, i would like to make a reservation with.", "role": "user", "streaming_reasoning": "The user mentions Yes, i would like to make a reservation with. It is not yet cle...
{ "answer": "I can help with the attraction. Could you share the area, type?", "reasoning": "Across the dialogue, the user is searching for particular piece of. Key context: yes, i would like to make a reservation with; i also have a book; on her husband; uh, acs canalis. The answer should focus on the latest user ...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2212", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007315
train
audio
multi_turn
[ { "role": "user", "text": "ye. and i want to have indian food in the moderate price range.", "turn_id": 1 }, { "role": "assistant", "text": "i prefer curry prints, please.", "turn_id": 2 }, { "role": "user", "text": "so can you help me to book a table for three people after 5...
{ "chunk_text": "Chunk 1: ye. and i want to have indian food in the moderate price range.\nChunk 2: i prefer curry prints, please.\nChunk 3: so can you help me to book a table for three people after 5 p m. and on the third day of week.\nChunk 4: ya.\nChunk 5: yes, that is fine. terrific.\nChunk 6: my name is abigail ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "ye. and i want to have indian food in the moderate price range.", "role": "user", "streaming_reasoning": "The user mentions Ye. It is not yet clear whether the user need...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is wanting to book table for three people after 5 p m. Key context: and i want to have indian food in the moderate price range; i prefer curry prints, please; so c...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1194", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007316
train
audio
multi_turn
[ { "role": "user", "text": "no, that'll be all.", "turn_id": 1 }, { "role": "assistant", "text": "yes, you can. can i give you my email address.", "turn_id": 2 }, { "role": "user", "text": "okay, so it's rb.", "turn_id": 3 }, { "role": "assistant", "text": "r o...
{ "chunk_text": "Chunk 1: no, that'll be all.\nChunk 2: yes, you can. can i give you my email address.\nChunk 3: okay, so it's rb.\nChunk 4: r o ck.\nChunk 5: t q j.\nChunk 6: a.\nChunk 7: at hotmail dot com.\nChunk 8: that is correct. yes.", "dialogue_text": "Chunk 1: no, that'll be all.\nChunk 2: yes, you can. ca...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "no, that'll be all.", "role": "user", "streaming_reasoning": "The user mentions No, that'll be all. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is talking about no, that'll be all. Key context: no, that'll be all; yes, you can; can i give you my email address; okay, so it's rb. The answer should focus on the latest user turn while incorporating rele...
{ "category": "work_productivity", "subcategory": "meeting_summary", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1077", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007317
train
audio
multi_turn
[ { "role": "user", "text": "and the restaurant should be in the boundary price range, please.", "turn_id": 1 }, { "role": "assistant", "text": "let us that's fine by me, ma'am.", "turn_id": 2 }, { "role": "user", "text": "yes. can i get the address, please.", "turn_id": 3 ...
{ "chunk_text": "Chunk 1: and the restaurant should be in the boundary price range, please.\nChunk 2: let us that's fine by me, ma'am.\nChunk 3: yes. can i get the address, please.\nChunk 4: thank you very much, sam.\nChunk 5: yes, we are. i'm also looking for a train.\nChunk 6: yes, it's 15 hours now. and the the tr...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and the restaurant should be in the boundary price range, please.", "role": "user", "streaming_reasoning": "The user mentions talking about should. It is not yet clear w...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: and the restaurant should be in the boundary price range, please; let us that's fine by me, ma'am; can i get the address, please; thank you very much, sam. The ...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0972", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007318
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, sure. please. i want to find an attraction that is in the east part of cambridge, can you help me.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, sure. please. i want to find an attraction that is in the east part of cambridge, can you help me.", "dialogue_text": "Chunk 1: hello.\nChunk 2: yes, sure. please. i want to find an attraction that is in the east part of cambridge, can you help me.", "instruction": ...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the attraction. Could you share the type?", "reasoning": "Across the dialogue, the user discusses \"hello.\" over 2 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user discusse...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1244", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007319
train
audio
multi_turn
[ { "role": "user", "text": "what time will arrive.", "turn_id": 1 }, { "role": "assistant", "text": "do you have a ticket for me.", "turn_id": 2 }, { "role": "user", "text": "that's perfect. thanks.", "turn_id": 3 }, { "role": "assistant", "text": "give you som...
{ "chunk_text": "Chunk 1: what time will arrive.\nChunk 2: do you have a ticket for me.\nChunk 3: that's perfect. thanks.\nChunk 4: give you some.\nChunk 5: sickness. 8 6 5 0 1 5.\nChunk 6: 4 0 4 0 7 6.\nChunk 7: 1 6 0.\nChunk 8: it will just be myself.", "dialogue_text": "Chunk 1: what time will arrive.\nChunk 2: ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "what time will arrive.", "role": "user", "streaming_reasoning": "The user mentions What time will arrive. It is not yet clear whether the user needs the full scope of th...
{ "answer": "Sure. I can provide the arriveby for the matching train option.", "reasoning": "Across the dialogue, the user is talking about what time will arrive. Key context: what time will arrive; do you have a ticket for me; that's perfect; give you some. The answer should focus on the latest user turn while inc...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3702", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002216
train
audio
multi_turn
[ { "role": "user", "text": "Human: Haha at least they have all their basis covered. Do you know any popular science fiction films that won Oscars? I know John Williams won a bunch for composing the Star Wars Music, but I wonder ", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I h...
{ "chunk_text": "Chunk 1: Human: Haha at least they have all their basis covered. Do you know any popular science fiction films that won Oscars? I know John Williams won a bunch for composing the Star Wars Music, but I wonder if any of them won for best picture?\nChunk 2: Assistant: I honestly can say I do not rememb...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Haha at least they have all their basis covered. Do you know any popular science fiction films that won Oscars? I know John Williams won a bunch for composing the Star Wars M...
{ "answer": "Off the top of my head I can't think of one. I love movies dealing with aliens and such though. I also enjoy when the sci fi has a little bit of a fear element to it.", "reasoning": "Across the dialogue, the user is asking for help with human: haha at least they have all their basis covered. Key contex...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_96578d43-347b-4936-8603-aff6a3421788", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007320
train
audio
multi_turn
[ { "role": "user", "text": "hello. have i reached customer service.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i'm playing at jump in cambridge.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for particular information regarding a train.", "turn_id": 3...
{ "chunk_text": "Chunk 1: hello. have i reached customer service.\nChunk 2: hi, i'm playing at jump in cambridge.\nChunk 3: i'm looking for particular information regarding a train.\nChunk 4: it's a departing from cambridge.\nChunk 5: lester.\nChunk 6: it's leaving on monday.\nChunk 7: and after 10.", "dialogue_tex...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. have i reached customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello. have i reached customer service. It is not yet clear whether t...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for particular information regarding a train. Key context: have i reached customer service; hi, i'm playing at jump in cambridge; i'm looking for particular information regarding a tra...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3423", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002217
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yup. Baker Mayfield from the University of OK played in a pretty large stadium.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes he did. Players can do more than just football to earn money though. Russell WIlson was under contract with the T...
{ "chunk_text": "Chunk 1: Human: Yup. Baker Mayfield from the University of OK played in a pretty large stadium.\nChunk 2: Assistant: Yes he did. Players can do more than just football to earn money though. Russell WIlson was under contract with the Texas Rangers baseball team til last year.\nChunk 3: Human: And Bake...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yup. Baker Mayfield from the University of OK played in a pretty large stadium.", "role": "user", "streaming_reasoning": "The user mentions talking about Human, B...
{ "answer": "Now that's interesting! The military football teams coaches work for the department of defense. They are the highest paid employees there.", "reasoning": "Across the dialogue, the user discusses \"Yup. Baker Mayfield from the University of OK played in a.\" over 3 turns. The answer should respond to th...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_96461533-b83b-4bbe-8c56-d87f885e75cd", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002218
train
audio
multi_turn
[ { "role": "user", "text": "Human: I love it! did you know iowa's locker room for their visitors is pink?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Iowa is trying some sort of mind game. I don't think it works well or other teams would imitate. How has Iowa done at home? Do...
{ "chunk_text": "Chunk 1: Human: I love it! did you know iowa's locker room for their visitors is pink?\nChunk 2: Assistant: Iowa is trying some sort of mind game. I don't think it works well or other teams would imitate. How has Iowa done at home? Do they win?\nChunk 3: Human: They are usually a pretty good home tea...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I love it! did you know iowa's locker room for their visitors is pink?", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not ...
{ "answer": "Hey, that's great! The kids must love that sort of thing. So much money goes to football.", "reasoning": "Across the dialogue, the user discusses \"I love it! did you know iowa's locker room for their.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversa...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_bad4a692-87cc-4dbb-8315-6254332c2262", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007321
train
audio
multi_turn
[ { "role": "user", "text": "the train should go to a station. i don't really remember the name.", "turn_id": 1 }, { "role": "assistant", "text": "thank you so much. the first word in london and is only three words.", "turn_id": 2 }, { "role": "user", "text": "uh, first one, th...
{ "chunk_text": "Chunk 1: the train should go to a station. i don't really remember the name.\nChunk 2: thank you so much. the first word in london and is only three words.\nChunk 3: uh, first one, thank you.\nChunk 4: and i'm going to depart from. a very famous university of.\nChunk 5: yes, that's right. thank you.\...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "the train should go to a station. i don't really remember the name.", "role": "user", "streaming_reasoning": "The user mentions The train should go to a station. It is n...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is talking about the train should go to a station. Key context: the train should go to a station; i don't really remember the name; thank you so much; the first word in london and is only three wor...
{ "category": "education", "subcategory": "course_planning", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1726", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007322
train
audio
multi_turn
[ { "role": "user", "text": "no, that's all.", "turn_id": 1 }, { "role": "assistant", "text": "hello is that customer service center.", "turn_id": 2 }, { "role": "user", "text": "well i'm having my trip on a in cambridge now and i want to look for a train to live there could yo...
{ "chunk_text": "Chunk 1: no, that's all.\nChunk 2: hello is that customer service center.\nChunk 3: well i'm having my trip on a in cambridge now and i want to look for a train to live there could you please help\nChunk 4: me to find it\nChunk 5: um let me think i want to go with chester square to have a visit.\nChu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "no, that's all.", "role": "user", "streaming_reasoning": "The user signals they may be wrapping up: \"No, that's all.\". The assistant should be ready to conclude if no ...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for no, that's all. Key context: no, that's all; hello is that customer service center; well i'm having my trip on a in cambridge now and i want to look for a train to live there could...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0334", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007323
train
audio
multi_turn
[ { "role": "user", "text": "hello customer service.", "turn_id": 1 }, { "role": "assistant", "text": "thanks for picking up.", "turn_id": 2 }, { "role": "user", "text": "i'm jim. can you.", "turn_id": 3 }, { "role": "assistant", "text": "so i'm looking at the n...
{ "chunk_text": "Chunk 1: hello customer service.\nChunk 2: thanks for picking up.\nChunk 3: i'm jim. can you.\nChunk 4: so i'm looking at the nearest police station.\nChunk 5: no, not at all. i just need a police escort.\nChunk 6: thank you very much for your help.\nChunk 7: i'm situated in the city center right now...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello customer service. It is not yet clear whether the user needs the full scope of ...
{ "answer": "For police information, I can help provide the station details you need.", "reasoning": "Across the dialogue, the user is talking about police escort. Key context: hello customer service; thanks for picking up; so i'm looking at the nearest police station; no, not at all. The answer should focus on the...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1139", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002219
train
audio
multi_turn
[ { "role": "user", "text": "Human: I have not, have you?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: No, I haven't because it premiered on Facebook Watch and I don't use that function of the social media platform, do you?", "turn_id": 2 }, { "role": "user", "t...
{ "chunk_text": "Chunk 1: Human: I have not, have you?\nChunk 2: Assistant: No, I haven't because it premiered on Facebook Watch and I don't use that function of the social media platform, do you?\nChunk 3: Human: I do occasionally, but usually if something strikes my interest while browsing.", "dialogue_text": "Ch...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I have not, have you?", "role": "user", "streaming_reasoning": "The user mentions Human: I have not, have you?. It is not yet clear whether the user needs what sp...
{ "answer": "Would you be interested in watching that docuseries about him? Maybe they mention something about how the former Patriots player, Benjarvus Green-Ellis never fumbled the football in his career, that's impressive.", "reasoning": "The dialogue is about \"I have not, have you?\" The user later explains \"...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_b33b0f2a-9b11-4c3d-ac69-94d9dfa8d8c7", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007324
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "and hello, how are you.", "turn_id": 2 }, { "role": "user", "text": "i'm great. thanks. i'm looking for a place to stay in cambridge.", "turn_id": 3 }, { "role": "assistant", "...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: and hello, how are you.\nChunk 3: i'm great. thanks. i'm looking for a place to stay in cambridge.\nChunk 4: the hotel should be in the milton country park area and should be in the type of a guesthouse with free wifi.\nChunk 5: okay.\nChunk 6: the acorn guesthouse from.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the hotel. Could you share the area, price?", "reasoning": "Across the dialogue, the user is searching for place to stay in cambridge. Key context: and hello, how are you; i'm looking for a place to stay in cambridge; the hotel should be in the milton country park area and should be in ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2805", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007325
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm more thinking you are speaking to michael and i'm planning a trip to cambridge.", "turn_id": 2 }, { "role": "user", "text": "okay, so basically i'm looking for places to go to...
{ "chunk_text": "Chunk 1: hello, how are you.\nChunk 2: i'm more thinking you are speaking to michael and i'm planning a trip to cambridge.\nChunk 3: okay, so basically i'm looking for places to go to in town. the attraction should be on opposite of the house.\nChunk 4: yes, i want the attraction should it should be ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Hello, how are you. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for places to go to in town. Key context: hello, how are you; i'm more thinking you are speaking to michael and i'm planning a trip to cambridge; okay, so basically i'm loo...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1593", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007326
train
audio
multi_turn
[ { "role": "user", "text": "okay. and do you have the address.", "turn_id": 1 }, { "role": "assistant", "text": "okay. and.", "turn_id": 2 }, { "role": "user", "text": "oh, okay. and do you know the operating hours.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: okay. and do you have the address.\nChunk 2: okay. and.\nChunk 3: oh, okay. and do you know the operating hours.\nChunk 4: okay, great. thanks.\nChunk 5: no, thank you. i think i have everything.\nChunk 6: but i would like to book a taxi.\nChunk 7: sure. it's 0 4, 4.\nChunk 8: 9, 7, 1.", "...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. and do you have the address.", "role": "user", "streaming_reasoning": "The user mentions Okay. and do you have the address. It is not yet clear whether the user ne...
{ "answer": "I can help book that. Could you provide the departure, destination, time?", "reasoning": "Across the dialogue, the user is wanting to book taxi. Key context: and do you have the address; and do you know the operating hours; okay, great; no, thank you. The answer should focus on the latest user turn whi...
{ "category": "finance_consumer", "subcategory": "budget_planning", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3049", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000255
train
audio
multi_turn
[ { "role": "user", "text": "In other words, these three men took down the lectures which Luther addressed to his students in the course of Galatians and", "turn_id": 1 }, { "role": "assistant", "text": "Roerer prepared the manuscript for the printer.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: In other words, these three men took down the lectures which Luther addressed to his students in the course of Galatians and\nChunk 2: Roerer prepared the manuscript for the printer.", "dialogue_text": "Chunk 1: In other words, these three men took down the lectures which Luther addressed ...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "In other words, these three men took down the lectures which Luther addressed to his students in the course of Galatians and", "role": "user", "streaming_reasoning": "Th...
{ "answer": "Could you repeat that? It's a bit noisy here with all the games going on.", "reasoning": "Across the dialogue, the user discusses \"In other words, these three men took down the lectures.\" over 2 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.",...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SD-Eval", "dialogue_id": "2830-3979-0008-gym", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007327
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a place to stay. can you help.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a place to stay. can you help.", "dialogue_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a place to stay. can you help.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chu...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: yes, i'm looking for a place to stay; can you help. The answer should focus on the latest user turn while incorporating relevant context fro...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0074", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002220
train
audio
multi_turn
[ { "role": "user", "text": "Human: Hello.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Hello.", "turn_id": 2 }, { "role": "user", "text": "Human: So, did you see Solo?", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: Human: Hello.\nChunk 2: Assistant: Hello.\nChunk 3: Human: So, did you see Solo?", "dialogue_text": "Chunk 1: Human: Hello.\nChunk 2: Assistant: Hello.\nChunk 3: Human: So, did you see Solo?", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revea...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Hello.", "role": "user", "streaming_reasoning": "The user mentions Human: Hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "Yes. I believe there was much missed opportunity in the film.", "reasoning": "Across the dialogue, the user discusses \"Hello.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user disc...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "easy", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_39d3ba64-ceda-40ec-8175-8024505c829f", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007328
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm doing well. thank you.", "turn_id": 2 }, { "role": "user", "text": "uh, i need some information. i'm looking for an attraction.", "turn_id": 3 }, { "role": "assist...
{ "chunk_text": "Chunk 1: hello, how are you.\nChunk 2: i'm doing well. thank you.\nChunk 3: uh, i need some information. i'm looking for an attraction.\nChunk 4: it's called the king hedges lena pool.\nChunk 5: okay. can i get the entrance 3 for that attraction.\nChunk 6: okay. uh, what about the. area what area is ...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Hello, how are you. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "Sure. I can provide the fee, area, postcode for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for attraction. Key context: hello, how are you; i'm doing well; uh, i need some information; i'm looking for an attraction. The answer should focus on the latest u...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3837", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_007329
train
audio
multi_turn
[ { "role": "user", "text": "4, 3, 8, 3.", "turn_id": 1 }, { "role": "assistant", "text": "7 3 1.", "turn_id": 2 }, { "role": "user", "text": "no, that will be fine. thank you. i'm also looking for a restaurant in a moderate price for serving seafood. i'd like to eat fish.", ...
{ "chunk_text": "Chunk 1: 4, 3, 8, 3.\nChunk 2: 7 3 1.\nChunk 3: no, that will be fine. thank you. i'm also looking for a restaurant in a moderate price for serving seafood. i'd like to eat fish.\nChunk 4: the area is fine.\nChunk 5: thank you.\nChunk 6: can you maybe find something that sells chinese food.\nChunk 7:...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "4, 3, 8, 3.", "role": "user", "streaming_reasoning": "The user mentions 4, 3, 8, 3. It is not yet clear whether the user needs the full scope of the user's request. The ...
{ "answer": "I can help book that. Could you provide the area?", "reasoning": "Across the dialogue, the user is searching for restaurant in a moderate price for serving seafood. Key context: no, that will be fine; i'm also looking for a restaurant in a moderate price for serving seafood; i'd like to eat fish; the a...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2060", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_002221
train
audio
multi_turn
[ { "role": "user", "text": "Human: Really???? Wow, I did not know that. Thanks for sharing", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: No problem! it is bordered by the Northern Territory, South Australia and New South Wales to the west, south-west and south respectively.", ...
{ "chunk_text": "Chunk 1: Human: Really???? Wow, I did not know that. Thanks for sharing\nChunk 2: Assistant: No problem! it is bordered by the Northern Territory, South Australia and New South Wales to the west, south-west and south respectively.\nChunk 3: Human: Crazy! Speaking of crazy... The development of the di...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Really???? Wow, I did not know that. Thanks for sharing", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Really, Thanks. It is not...
{ "answer": "Wow! That is crazy!", "reasoning": "Across the dialogue, the user is reporting a problem with human: really. Key context: Human: Really; Wow, I did not know that; Thanks for sharing Assistant: No problem; it is bordered by the Northern Territory, South Australia and New South Wales to the west, south-w...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_80cd2d93-42df-4474-8149-1c1e7027ee16", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }