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_multidialog_v02_000360
train
audio
multi_turn
[ { "role": "user", "text": "Human: No, is he another QB?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes, and he's the only one in NFL history to throw a touchdown pass to himself. He won the Super Bowl", "turn_id": 2 }, { "role": "user", "text": "Human: Thats...
{ "chunk_text": "Chunk 1: Human: No, is he another QB?\nChunk 2: Assistant: Yes, and he's the only one in NFL history to throw a touchdown pass to himself. He won the Super Bowl\nChunk 3: Human: Thats awesome I wonder how he did that lol, MVP for sure, he threw the pass and caught it", "dialogue_text": "Chunk 1: Hu...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: No, is he another QB?", "role": "user", "streaming_reasoning": "The user mentions Human: No, is he another QB?. It is not yet clear whether the user needs what sp...
{ "answer": "Definitely. Only two African American QBs have won the Super Bowl, and both beat the Broncos when doing so", "reasoning": "Across the dialogue, the user discusses \"No, is he another QB?\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", ...
{ "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_9004d787-4941-4c96-9ce7-b261cbb2a45e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001201
train
audio
multi_turn
[ { "role": "user", "text": "and t a n d o o r i for tender", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'd like to know the address of the restaurant.", "turn_id": 2 }, { "role": "user", "text": "uh, i'm sorry, i didn't catch you can repeat.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: and t a n d o o r i for tender\nChunk 2: yes, i'd like to know the address of the restaurant.\nChunk 3: uh, i'm sorry, i didn't catch you can repeat.\nChunk 4: okay glad to know that and also please help me find a hotel the name is alpha milton it's m i l t o n\nChunk 5: for milton alpha mil...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and t a n d o o r i for tender", "role": "user", "streaming_reasoning": "The user mentions And t a n d o o r i for tender. It is not yet clear whether the user needs the...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for taxi for me to commute between their two places. Key context: and t a n d o o r i for tender yes, i'd like to know the address of the restaurant; uh, i'm sorry, i didn't c...
{ "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": "MUL0958", "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_001202
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "good afternoon is the information center of cambridge.", "turn_id": 2 }, { "role": "user", "text": "well, um, i'm looking for some information.", "turn_id": 3 }, { "role": "assista...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: good afternoon is the information center of cambridge.\nChunk 3: well, um, i'm looking for some information.\nChunk 4: yes. um, there is a there is an. um there's a serious accident.\nChunk 5: well, it should it's a car accident.\nChunk 6: um thing after the accident there t...
{ "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": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is searching for information. Key context: good afternoon is the information center of cambridge; well, um, i'm looking for some information; um, there is a there is an; um there's a serious accident. The an...
{ "category": "social_communication", "subcategory": "conflict_deescalation", "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": "SNG0041", "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_001203
train
audio
multi_turn
[ { "role": "user", "text": "my id number is 4 4, 4 5.", "turn_id": 1 }, { "role": "assistant", "text": "9 5 9 7.", "turn_id": 2 }, { "role": "user", "text": "9 4 3 9.", "turn_id": 3 }, { "role": "assistant", "text": "3 7 4 2.", "turn_id": 4 }, { "ro...
{ "chunk_text": "Chunk 1: my id number is 4 4, 4 5.\nChunk 2: 9 5 9 7.\nChunk 3: 9 4 3 9.\nChunk 4: 3 7 4 2.\nChunk 5: and i'm booking it for myself and for my colleagues, right.\nChunk 6: oh, okay.\nChunk 7: um. yes, please.\nChunk 8: alright, thank you so much.", "dialogue_text": "Chunk 1: my id number is 4 4, 4 ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "my id number is 4 4, 4 5.", "role": "user", "streaming_reasoning": "The user mentions My id number is 4 4, 4 5. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help book that. Could you provide the departure, destination, day?", "reasoning": "Across the dialogue, the user is wanting to book my id number is 4 4, 4 5. Key context: my id number is 4 4, 4 5; and i'm booking it for myself and for my colleagues, right; yes, please; alright, thank you so much....
{ "category": "work_productivity", "subcategory": "meeting_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": "MUL3562", "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_001204
train
audio
multi_turn
[ { "role": "user", "text": "hello. is this customer service.", "turn_id": 1 }, { "role": "assistant", "text": "yes. and i wonder if you could find me a particular attraction.", "turn_id": 2 }, { "role": "user", "text": "uh, i remember called the fifth william museum.", "tu...
{ "chunk_text": "Chunk 1: hello. is this customer service.\nChunk 2: yes. and i wonder if you could find me a particular attraction.\nChunk 3: uh, i remember called the fifth william museum.\nChunk 4: okay, thank you.", "dialogue_text": "Chunk 1: hello. is this customer service.\nChunk 2: yes. and i wonder if you c...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. is this customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello. is this customer service. It is not yet clear whether the user needs ...
{ "answer": "I can help with the attraction. Could you share the area, type?", "reasoning": "Across the dialogue, the user is searching for particular attraction. Key context: is this customer service; and i wonder if you could find me a particular attraction; uh, i remember called the fifth william museum; okay, t...
{ "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": "MUL1751", "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_001205
train
audio
multi_turn
[ { "role": "user", "text": "3, 5, 5.", "turn_id": 1 }, { "role": "assistant", "text": "1 5 9 all right great thank you very much i'm also looking for a restaurant that serves food from south asia and should be", "turn_id": 2 }, { "role": "user", "text": "off the expensive pric...
{ "chunk_text": "Chunk 1: 3, 5, 5.\nChunk 2: 1 5 9 all right great thank you very much i'm also looking for a restaurant that serves food from south asia and should be\nChunk 3: off the expensive price range do you have such a restaurant\nChunk 4: that's right.\nChunk 5: all right. could you give me maybe three of th...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "3, 5, 5.", "role": "user", "streaming_reasoning": "The user mentions 3, 5, 5. It is not yet clear whether the user needs the full scope of the user's request. The assist...
{ "answer": "Sure. I can provide the postcode for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for restaurant that serves food from south asia. Key context: 1 5 9 all right great thank you very much i'm also looking for a restaurant that serves food from south asia and ...
{ "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": "MUL3325", "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_000361
train
audio
multi_turn
[ { "role": "user", "text": "Human: lol the struggle is real. I cant believe that the average nfl game has only 11 min of game play.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I feel like there are too many commercials and replays and measurements.", "turn_id": 2 }, {...
{ "chunk_text": "Chunk 1: Human: lol the struggle is real. I cant believe that the average nfl game has only 11 min of game play.\nChunk 2: Assistant: I feel like there are too many commercials and replays and measurements.\nChunk 3: Human: Yeah, too much fluff. and whats with all the time outs and fouls and huddles....
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: lol the struggle is real. I cant believe that the average nfl game has only 11 min of game play.", "role": "user", "streaming_reasoning": "The user mentions talki...
{ "answer": "Maybe that's why i usually drink too much watching the games.", "reasoning": "Across the dialogue, the user discusses \"lol the struggle is real. I cant believe that the average.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "respo...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "emotional_expression" }
{ "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_7c384d58-a48a-448c-a1c8-6797d4d0cab7", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000042
train
audio
multi_turn
[ { "role": "user", "text": "Both the conditions and the complicity are documented in considerable detail.", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: Both the conditions and the complicity are documented in considerable detail.", "dialogue_text": "Chunk 1: Both the conditions and the complicity are documented in considerable detail.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed au...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Both the conditions and the complicity are documented in considerable detail.", "role": "user", "streaming_reasoning": "The user mentions talking about Both. It is not y...
{ "answer": "That's fantastic! It's great to see such thorough documentation. It really helps in understanding the full scope of the situation.", "reasoning": "Across the dialogue, the user discusses \"Both the conditions and the complicity are documented in.\" over 1 turns. The answer should respond to the latest ...
{ "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": "M019_happy_level3_020", "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_001206
train
audio
multi_turn
[ { "role": "user", "text": "is the customer service of cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "yes, with information in cambridge.", "turn_id": 2 }, { "role": "user", "text": "well, i'm looking for a place to dine.", "turn_id": 3 }, { "role": "...
{ "chunk_text": "Chunk 1: is the customer service of cambridge.\nChunk 2: yes, with information in cambridge.\nChunk 3: well, i'm looking for a place to dine.\nChunk 4: yes, i suppose the restaurant should be in the center.\nChunk 5: that's right. and also it's true serve european food.", "dialogue_text": "Chunk 1:...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "is the customer service of cambridge.", "role": "user", "streaming_reasoning": "The user mentions Is the customer service of cambridge. It is not yet clear whether the u...
{ "answer": "I can help with the restaurant. Could you share the price?", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: is the customer service of cambridge; yes, with information in cambridge; well, i'm looking for a place to dine; yes, i suppose the restaurant should be ...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "SNG0783", "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_001207
train
audio
multi_turn
[ { "role": "user", "text": "oh. 8 2. 7, 9.", "turn_id": 1 }, { "role": "assistant", "text": "7, 6.", "turn_id": 2 }, { "role": "user", "text": "5, 4.", "turn_id": 3 }, { "role": "assistant", "text": "double q.", "turn_id": 4 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: oh. 8 2. 7, 9.\nChunk 2: 7, 6.\nChunk 3: 5, 4.\nChunk 4: double q.\nChunk 5: thirtyfour.\nChunk 6: 1, 5, 8.\nChunk 7: no.\nChunk 8: ya you forgot to make a working for five people.", "dialogue_text": "Chunk 1: oh. 8 2. 7, 9.\nChunk 2: 7, 6.\nChunk 3: 5, 4.\nChunk 4: double q.\nChunk 5: thi...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "oh. 8 2. 7, 9.", "role": "user", "streaming_reasoning": "The user mentions Oh. 8 2. 7, 9. It is not yet clear whether the user needs the full scope of the user's request...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is talking about ya you forgot to make a working for five people. Key context: ya you forgot to make a working for five people. The answer should focus on the latest user turn while...
{ "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": "MUL2886", "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_001208
train
audio
multi_turn
[ { "role": "user", "text": "hello, i like to make a booking for taxi.", "turn_id": 1 }, { "role": "assistant", "text": "okay, i'm. departing from people's portraits exhibition at girton college and heading to. la mosa.", "turn_id": 2 }, { "role": "user", "text": "oh, yes, i'm ...
{ "chunk_text": "Chunk 1: hello, i like to make a booking for taxi.\nChunk 2: okay, i'm. departing from people's portraits exhibition at girton college and heading to. la mosa.\nChunk 3: oh, yes, i'm living after 1045 am.\nChunk 4: okay.\nChunk 5: yes, my phone number 8 1 double 6 5.\nChunk 6: 1 8 4 2 7.\nChunk 7: uh...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, i like to make a booking for taxi.", "role": "user", "streaming_reasoning": "The user mentions Hello, i like to make a booking for taxi. It is not yet clear wheth...
{ "answer": "Sure. I can provide the car for the matching taxi option.", "reasoning": "Across the dialogue, the user is wanting to book hello, i like to make a booking for taxi. Key context: hello, i like to make a booking for taxi; departing from people's portraits exhibition at girton college and heading to; oh, ...
{ "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": "SNG1389", "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_000362
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yes, I hope to see them there at some point. There are only 11 minutes of active game play", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Sounds light, but I bet there are better jobs for them. The average lifetime earnings of an engineer are h...
{ "chunk_text": "Chunk 1: Human: Yes, I hope to see them there at some point. There are only 11 minutes of active game play\nChunk 2: Assistant: Sounds light, but I bet there are better jobs for them. The average lifetime earnings of an engineer are higher than the average lifetime earnings of an NFL player.\nChunk 3...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yes, I hope to see them there at some point. There are only 11 minutes of active game play", "role": "user", "streaming_reasoning": "The user mentions talking abo...
{ "answer": "Did you know that New Orleans Saints cheerleaders cannot eat in the same restaurant as any NFL player? Seems sexist to me.", "reasoning": "Across the dialogue, the user is asking for help with human: yes, i hope to see them there at some point. Key context: Human: Yes, I hope to see them there at some ...
{ "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_be3751f6-0d06-4474-b827-46431a10e7dc", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001209
train
audio
multi_turn
[ { "role": "user", "text": "yes, i want to depart from cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "yeah, i want to leave on wednesday.", "turn_id": 2 }, { "role": "user", "text": "okay, thank you.", "turn_id": 3 }, { "role": "assistant", "text"...
{ "chunk_text": "Chunk 1: yes, i want to depart from cambridge.\nChunk 2: yeah, i want to leave on wednesday.\nChunk 3: okay, thank you.\nChunk 4: yes, yes. uh, please book for three people. that's three tickets.\nChunk 5: yes, my id number is 2 2, 5, 0.\nChunk 6: uh, 7 8 2.\nChunk 7: on 0 6, 3, 7.\nChunk 8: a 9 9 9 ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, i want to depart from cambridge.", "role": "user", "streaming_reasoning": "The user mentions Yes, i want to depart from cambridge. It is not yet clear whether the u...
{ "answer": "I can help book that. Could you provide the destination, time?", "reasoning": "Across the dialogue, the user is wanting to book for three people. Key context: yes, i want to depart from cambridge; yeah, i want to leave on wednesday; okay, thank you; uh, please book for three people. 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": "MUL1067", "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_001210
train
audio
multi_turn
[ { "role": "user", "text": "okay, then four star would be okay.", "turn_id": 1 }, { "role": "assistant", "text": "yeah sure please book rooms for me and we have 7 people all together and we're going to spend starting from friday and we will", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: okay, then four star would be okay.\nChunk 2: yeah sure please book rooms for me and we have 7 people all together and we're going to spend starting from friday and we will\nChunk 3: leave on sunday\nChunk 4: correct.\nChunk 5: yes, it's virtue to silver.\nChunk 6: i s g e r t r u d e for ge...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, then four star would be okay.", "role": "user", "streaming_reasoning": "The user mentions Okay, then four star would be okay. It is not yet clear whether the user ...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book rooms for me. Key context: okay, then four star would be okay; yeah sure please book rooms for me and we have 7 people all together and we're going to spend starting fro...
{ "category": "work_productivity", "subcategory": "meeting_summary", "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": "MUL0165", "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_001211
train
audio
multi_turn
[ { "role": "user", "text": "i also need a place to stay.", "turn_id": 1 }, { "role": "assistant", "text": "uh yes, the type. will be the regular.", "turn_id": 2 }, { "role": "user", "text": "yeah, that's right. thank you.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: i also need a place to stay.\nChunk 2: uh yes, the type. will be the regular.\nChunk 3: yeah, that's right. thank you.\nChunk 4: yes, please make it include free wifi.\nChunk 5: and let's make it in the same area as restaurant.\nChunk 6: yeah, that's right. thank you.\nChunk 7: okay. thank y...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i also need a place to stay.", "role": "user", "streaming_reasoning": "The user mentions I also need a place to stay. It is not yet clear whether the user needs the full...
{ "answer": "I can help book that. Could you provide the price, day, stay_length?", "reasoning": "Across the dialogue, the user is wanting to book it for me. Key context: i also need a place to stay; uh yes, the type; will be the regular; yeah, that's right. The answer should focus on the latest user turn while inc...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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": "MUL3858", "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_001212
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi i was looking for a train departing from cambridge and i'd like to arrive by three forty five pm tuesday january tenth and i'm", "turn_id": 2 }, { "role": "user", "text": "going to that big...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi i was looking for a train departing from cambridge and i'd like to arrive by three forty five pm tuesday january tenth and i'm\nChunk 3: going to that big town near bruno\nChunk 4: sounds great if i could book that for four people, please.", "dialogue_text": "Chunk 1: h...
{ "num_checkpoints": 4, "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 with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for train departing from cambridge. The answer should focus on the latest user turn while incorporating relevant context from earlier turns.", "resp...
{ "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": "SNG1668", "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_001213
train
audio
multi_turn
[ { "role": "user", "text": "yes. and i will depart from a name, a place named c. e. m. b. or something.", "turn_id": 1 }, { "role": "assistant", "text": "yes, cambridge is right.", "turn_id": 2 }, { "role": "user", "text": "and i will go to a, please name the b, r, oxor someth...
{ "chunk_text": "Chunk 1: yes. and i will depart from a name, a place named c. e. m. b. or something.\nChunk 2: yes, cambridge is right.\nChunk 3: and i will go to a, please name the b, r, oxor something, you know.\nChunk 4: okay. thank you.\nChunk 5: yes, brooks, for me is right.\nChunk 6: um that's all my comments....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes. and i will depart from a name, a place named c. e. m. b. or something.", "role": "user", "streaming_reasoning": "The user mentions Yes. It is not yet clear whether ...
{ "answer": "I can help with the train. Could you share the day, time?", "reasoning": "Across the dialogue, the user is asking for help with and i will depart from a name, a place named c. Key context: and i will depart from a name, a place named c; or something; yes, cambridge is right; and i will go to a, please ...
{ "category": "education", "subcategory": "course_planning", "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": "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_spokenwoz_v02_001214
train
audio
multi_turn
[ { "role": "user", "text": "uh yes, the type. will be the regular.", "turn_id": 1 }, { "role": "assistant", "text": "yeah, that's right. thank you.", "turn_id": 2 }, { "role": "user", "text": "yes, please make it include free wifi.", "turn_id": 3 }, { "role": "assi...
{ "chunk_text": "Chunk 1: uh yes, the type. will be the regular.\nChunk 2: yeah, that's right. thank you.\nChunk 3: yes, please make it include free wifi.\nChunk 4: and let's make it in the same area as restaurant.\nChunk 5: yeah, that's right. thank you.\nChunk 6: okay. thank you.\nChunk 7: okay, sounds lovely. can ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh yes, the type. will be the regular.", "role": "user", "streaming_reasoning": "The user mentions Uh yes, the type. will be the regular. It is not yet clear whether the...
{ "answer": "I can help book that. Could you provide the price, day, stay_length?", "reasoning": "Across the dialogue, the user is wanting to book it for me. Key context: uh yes, the type; will be the regular; yeah, that's right; yes, please make it include free wifi. The answer should focus on the latest user turn...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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": "MUL3858", "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_001215
train
audio
multi_turn
[ { "role": "user", "text": "i'm also looking for a train.", "turn_id": 1 }, { "role": "assistant", "text": "and the train should leave after 8 pm on the same day of the hotel bk.", "turn_id": 2 }, { "role": "user", "text": "ministry depart from indian station to cambridge.", ...
{ "chunk_text": "Chunk 1: i'm also looking for a train.\nChunk 2: and the train should leave after 8 pm on the same day of the hotel bk.\nChunk 3: ministry depart from indian station to cambridge.\nChunk 4: can you please get me the train id and the price.\nChunk 5: okay.\nChunk 6: i know. that's all.\nChunk 7: no tw...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm also looking for a train.", "role": "user", "streaming_reasoning": "The user mentions I'm also looking for a train. It is not yet clear whether the user needs the fu...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is searching for train. Key context: i'm also looking for a train; and the train should leave after 8 pm on the same day of the hotel bk; ministry depart from indian station to cambridge; can you ...
{ "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": "MUL2646", "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_001216
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.\nChunk 6: okay great can...
{ "num_checkpoints": 8, "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 book that. Could you provide the day, time?", "reasoning": "Across the dialogue, the user is searching for table for me we have let me see my family. Key context: oh, i want to eat in the downtown of this city; please help me find a restaurant; i prefer some turkish food; in a cheap price, p...
{ "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": "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_001217
train
audio
multi_turn
[ { "role": "user", "text": "hi, hello.", "turn_id": 1 }, { "role": "assistant", "text": "couldn't yourself.", "turn_id": 2 }, { "role": "user", "text": "i need your assistance.", "turn_id": 3 }, { "role": "assistant", "text": "so i'm looking for a place to stay...
{ "chunk_text": "Chunk 1: hi, hello.\nChunk 2: couldn't yourself.\nChunk 3: i need your assistance.\nChunk 4: so i'm looking for a place to stay, right.", "dialogue_text": "Chunk 1: hi, hello.\nChunk 2: couldn't yourself.\nChunk 3: i need your assistance.\nChunk 4: so i'm looking for a place to stay, right.", "in...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, hello.", "role": "user", "streaming_reasoning": "The user mentions Hi, hello. It is not yet clear whether the user needs the full scope of the user's request. The as...
{ "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: couldn't yourself; i need your assistance; so i'm looking for a place to stay, right. The answer should focus on the latest user turn while ...
{ "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": "SNG0955", "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_000363
train
audio
multi_turn
[ { "role": "user", "text": "Human: No I'm not sure how long, but if I had to take a guess I would say one year? Am I close?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: No, I guess it was only two and a half hours! He got paid $7500, but that was good money for under three hou...
{ "chunk_text": "Chunk 1: Human: No I'm not sure how long, but if I had to take a guess I would say one year? Am I close?\nChunk 2: Assistant: No, I guess it was only two and a half hours! He got paid $7500, but that was good money for under three hours of work!\nChunk 3: Human: oh my goodness! That is a great payche...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: No I'm not sure how long, but if I had to take a guess I would say one year? Am I close?", "role": "user", "streaming_reasoning": "The user mentions talking about...
{ "answer": "Yeah right, good money for the time as well. Did you know Al Pacino turned down the role of Han Solo?", "reasoning": "Across the dialogue, the user is asking for help with human: no i'm not sure how long, but if i had to take a guess i would say one year. Key context: Human: No I'm not sure how long, b...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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_6e8dc0d9-4920-48b3-a62c-0844c44e8904", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001218
train
audio
multi_turn
[ { "role": "user", "text": "hi good morning i am looking for a particular attraction in town the name is called wendell berry country park do you have that on your system", "turn_id": 1 }, { "role": "assistant", "text": "all right, great. could you provide me with your phone number. opening h...
{ "chunk_text": "Chunk 1: hi good morning i am looking for a particular attraction in town the name is called wendell berry country park do you have that on your system\nChunk 2: all right, great. could you provide me with your phone number. opening hours as well as the entrance c.\nChunk 3: 1, 2, 2, 3.\nChunk 4: 2, ...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi good morning i am looking for a particular attraction in town the name is called wendell berry country park do you have that on your system", "role": "user", "streami...
{ "answer": "Sure. I can provide the phone, fee for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for wendell berry country park do you have that on your system all right. Key context: hi good morning i am looking for a particular attraction in town the name is called we...
{ "category": "daily_life", "subcategory": "home_task", "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": "SNG1439", "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_001219
train
audio
multi_turn
[ { "role": "user", "text": "yes, friday, please.", "turn_id": 1 }, { "role": "assistant", "text": "yes, it should depart from cambridge.", "turn_id": 2 }, { "role": "user", "text": "uh, i want to leave after ten forty five.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: yes, friday, please.\nChunk 2: yes, it should depart from cambridge.\nChunk 3: uh, i want to leave after ten forty five.\nChunk 4: and i want i want to go to peter brow.\nChunk 5: okay. if i want to make a booking, which one do you recommend.\nChunk 6: okay, great. sounds great.\nChunk 7: um...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, friday, please.", "role": "user", "streaming_reasoning": "The user mentions Yes, friday, please. It is not yet clear whether the user needs the full scope of the us...
{ "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 to leave after ten forty five. Key context: yes, friday, please; yes, it should depart from cambridge; uh, i want to leave after ten forty five;...
{ "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": "MUL3940", "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_000364
train
audio
multi_turn
[ { "role": "user", "text": "Human: I didnt hear about that, but I think they they are missing out on a high rating.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Agree. They want to replace Jon Gruden on Monday Night Football. He's back coaching the Raiders. Peyton Manning turn...
{ "chunk_text": "Chunk 1: Human: I didnt hear about that, but I think they they are missing out on a high rating.\nChunk 2: Assistant: Agree. They want to replace Jon Gruden on Monday Night Football. He's back coaching the Raiders. Peyton Manning turned down ESPN, too. Another ratings loss?\nChunk 3: Human: Could be,...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I didnt hear about that, but I think they they are missing out on a high rating.", "role": "user", "streaming_reasoning": "The user mentions talking about Human. ...
{ "answer": "Right. Favre had a 20-yr. career, a SB win, three NFL MVP awards, after all.", "reasoning": "Across the dialogue, the user discusses \"I didnt hear about that, but I think they they are missing.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational ...
{ "category": "social_communication", "subcategory": "invitation_response", "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_58d231e0-66fd-4615-a61f-4c4a8173ee52", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001220
train
audio
multi_turn
[ { "role": "user", "text": "okay, great. um, i want to. i want to know the um the address actually.", "turn_id": 1 }, { "role": "assistant", "text": "okay, maybe some people are. thank you. i already make write down.", "turn_id": 2 }, { "role": "user", "text": "yes. uh, can yo...
{ "chunk_text": "Chunk 1: okay, great. um, i want to. i want to know the um the address actually.\nChunk 2: okay, maybe some people are. thank you. i already make write down.\nChunk 3: yes. uh, can you please have a book. a taxi for me to go to the architecture and.\nChunk 4: mmhmm. so my telephone number is 7 4 5 0....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, great. um, i want to. i want to know the um the address actually.", "role": "user", "streaming_reasoning": "The user mentions talking about Okay. It is not yet cle...
{ "answer": "I can help book that. Could you provide the departure, destination?", "reasoning": "Across the dialogue, the user is wanting to book okay, great. Key context: okay, great; um, i want to; i want to know the um the address actually; okay, maybe some people are. The answer should focus on the latest user ...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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": "MUL1865", "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_000365
train
audio
multi_turn
[ { "role": "user", "text": "Human: I see that he secured funding through a private benefactor who turned out to be Denzel Washington!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Oh wow, noway! I didn't know that part of the story. How cool would that be! Washington made a goo...
{ "chunk_text": "Chunk 1: Human: I see that he secured funding through a private benefactor who turned out to be Denzel Washington!\nChunk 2: Assistant: Oh wow, noway! I didn't know that part of the story. How cool would that be! Washington made a good investment in the guy who turned out Black Panther,wow.\nChunk 3:...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I see that he secured funding through a private benefactor who turned out to be Denzel Washington!", "role": "user", "streaming_reasoning": "The user mentions tal...
{ "answer": "SO cool. Yes, I love Wonder Woman. The actress who plays her Gal Gadot didn't even know that she was auditioning for Wonder Woman at the time she was doing it.", "reasoning": "Across the dialogue, the user is asking for help with human: i see that he secured funding through a private benefactor who tur...
{ "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_f106cb12-02dc-45b0-bde8-f06360172d9c", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001221
train
audio
multi_turn
[ { "role": "user", "text": "hi, hello.", "turn_id": 1 }, { "role": "assistant", "text": "couldn't yourself.", "turn_id": 2 }, { "role": "user", "text": "i need your assistance.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hi, hello.\nChunk 2: couldn't yourself.\nChunk 3: i need your assistance.", "dialogue_text": "Chunk 1: hi, hello.\nChunk 2: couldn't yourself.\nChunk 3: i need your assistance.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/tran...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, hello.", "role": "user", "streaming_reasoning": "The user mentions Hi, hello. It is not yet clear whether the user needs the full scope of the user's request. The as...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is asking for help with your assistance. Key context: couldn't yourself; i need your assistance. The answer should focus on the latest user turn while incorporating relevant context from earlier turns.", "...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "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": "SNG0955", "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_001222
train
audio
multi_turn
[ { "role": "user", "text": "hi is the customer service.", "turn_id": 1 }, { "role": "assistant", "text": "uh, i'm looking for a theater to go in.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hi is the customer service.\nChunk 2: uh, i'm looking for a theater to go in.", "dialogue_text": "Chunk 1: hi is the customer service.\nChunk 2: uh, i'm looking for a theater to go in.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed au...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi is the customer service.", "role": "user", "streaming_reasoning": "The user mentions Hi is the customer service. It is not yet clear whether the user needs the full s...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for theater to go in. Key context: hi is the customer service; uh, i'm looking for a theater to go in. The answer should focus on the latest user turn while incorporating relevant contex...
{ "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": "SNG0330", "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_001223
train
audio
multi_turn
[ { "role": "user", "text": "um can you just repeat the first one first option.", "turn_id": 1 }, { "role": "assistant", "text": "aircon guesthouse. i think i prefer that.", "turn_id": 2 }, { "role": "user", "text": "uh, in what price rank is it.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: um can you just repeat the first one first option.\nChunk 2: aircon guesthouse. i think i prefer that.\nChunk 3: uh, in what price rank is it.\nChunk 4: okay, that's fine.\nChunk 5: um i'm also looking. yes, please. i'm also looking for a restaurant.\nChunk 6: the restaurant should serve chi...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um can you just repeat the first one first option.", "role": "user", "streaming_reasoning": "The user mentions Um can you just repeat the first one first option. It is n...
{ "answer": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: um can you just repeat the first one first option; aircon guesthouse; i think i prefer that; uh, in what price rank is it. The answer should focus on ...
{ "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": "MUL2813", "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_001224
train
audio
multi_turn
[ { "role": "user", "text": "restaurant and maybe you cannot find it that is fine but what you can't help me with is um", "turn_id": 1 }, { "role": "assistant", "text": "can you please book me a train uh that is deporting from cambridge and it should leave after quarter past 9 a m and the", ...
{ "chunk_text": "Chunk 1: restaurant and maybe you cannot find it that is fine but what you can't help me with is um\nChunk 2: can you please book me a train uh that is deporting from cambridge and it should leave after quarter past 9 a m and the\nChunk 3: trend should be leaving on wednesday and it should be going t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "restaurant and maybe you cannot find it that is fine but what you can't help me with is um", "role": "user", "streaming_reasoning": "The user mentions searching for Rest...
{ "answer": "Sure. I can provide the id for the matching train option.", "reasoning": "Across the dialogue, the user is searching for me a train uh that is deporting from cambridge. Key context: uh, is the chinese belief of the quarter; like, uh, the; so we had to show you that; yeah, if it is fine, may i please ge...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "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_spokenwoz_v02_001225
train
audio
multi_turn
[ { "role": "user", "text": "okay. and i think the i don't. the internet.", "turn_id": 1 }, { "role": "assistant", "text": "um let me see, i have so it would be. good to have free parking in the hotel.", "turn_id": 2 }, { "role": "user", "text": "i think the hotel should have o...
{ "chunk_text": "Chunk 1: okay. and i think the i don't. the internet.\nChunk 2: um let me see, i have so it would be. good to have free parking in the hotel.\nChunk 3: i think the hotel should have our 4.\nChunk 4: let me see, that's fine.\nChunk 5: yeah, sure. i'd like to book it for my parents and me for four nigh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. and i think the i don't. the internet.", "role": "user", "streaming_reasoning": "The user mentions Okay. and i think the i don't. the internet. It is not yet clear...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book it for my parents. Key context: and i think the i don't; the internet; um let me see, i have so it would be; good to have free parking in the hotel. The answer should fo...
{ "category": "education", "subcategory": "course_planning", "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": "MUL1958", "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_001226
train
audio
multi_turn
[ { "role": "user", "text": "es.", "turn_id": 1 }, { "role": "assistant", "text": "great. i also would like to attend a local tourist attraction.", "turn_id": 2 }, { "role": "user", "text": "is there a museum located close to the restaurant.", "turn_id": 3 }, { "rol...
{ "chunk_text": "Chunk 1: es.\nChunk 2: great. i also would like to attend a local tourist attraction.\nChunk 3: is there a museum located close to the restaurant.\nChunk 4: okay. do you know if there's an entrance fee for that.\nChunk 5: okay. and do you have the address.\nChunk 6: okay. and.\nChunk 7: oh, okay. and...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "es.", "role": "user", "streaming_reasoning": "The user mentions Es. It is not yet clear whether the user needs the full scope of the user's request. The assistant should...
{ "answer": "Sure. I can provide the fee, address for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for to attend a local tourist attraction. Key context: i also would like to attend a local tourist attraction; is there a museum located close to the restaurant; do you kn...
{ "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": "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_spokenwoz_v02_001227
train
audio
multi_turn
[ { "role": "user", "text": "oh. hello.", "turn_id": 1 }, { "role": "assistant", "text": "good day. i'm. feel for a place to go to income.", "turn_id": 2 }, { "role": "user", "text": "and the thing that i'm looking for should be a museum.", "turn_id": 3 }, { "role":...
{ "chunk_text": "Chunk 1: oh. hello.\nChunk 2: good day. i'm. feel for a place to go to income.\nChunk 3: and the thing that i'm looking for should be a museum.\nChunk 4: okay. can you please give me um the address on the opening hours.\nChunk 5: and also fit. oh, also the entrance fee.\nChunk 6: yeah.\nChunk 7: no, ...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "oh. hello.", "role": "user", "streaming_reasoning": "The user mentions Oh. hello. It is not yet clear whether the user needs the full scope of the user's request. The as...
{ "answer": "Sure. I can provide the address, fee for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for should be a museum. Key context: feel for a place to go to income; and the thing that i'm looking for should be a museum; can you please give me um the address on the ...
{ "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": "SNG0990", "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_001228
train
audio
multi_turn
[ { "role": "user", "text": "so my telephone number is 2 5 2 6 3 1.", "turn_id": 1 }, { "role": "assistant", "text": "6 4 6 0.", "turn_id": 2 }, { "role": "user", "text": "yes, that's correct.", "turn_id": 3 }, { "role": "assistant", "text": "okay. and can you p...
{ "chunk_text": "Chunk 1: so my telephone number is 2 5 2 6 3 1.\nChunk 2: 6 4 6 0.\nChunk 3: yes, that's correct.\nChunk 4: okay. and can you please tell me the phone of the phone number, the tax also.\nChunk 5: okay, great. thank you.\nChunk 6: and i also, uh, please tell you general that i want to leave the museum...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "so my telephone number is 2 5 2 6 3 1.", "role": "user", "streaming_reasoning": "The user mentions So my telephone number is 2 5 2 6 3 1. It is not yet clear whether the...
{ "answer": "Sure. I can provide the phone for the matching taxi option.", "reasoning": "Across the dialogue, the user is talking about to leave the museum. Key context: so my telephone number is 2 5 2 6 3 1; yes, that's correct; and can you please tell me the phone of the phone number, the tax also; okay, great. T...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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": "MUL1868", "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_001229
train
audio
multi_turn
[ { "role": "user", "text": "yes, it's 3 1, 6, 0.", "turn_id": 1 }, { "role": "assistant", "text": "8 8 5 3.", "turn_id": 2 }, { "role": "user", "text": "5 7 2 2.", "turn_id": 3 }, { "role": "assistant", "text": "9 4 1 7.", "turn_id": 4 }, { "role": ...
{ "chunk_text": "Chunk 1: yes, it's 3 1, 6, 0.\nChunk 2: 8 8 5 3.\nChunk 3: 5 7 2 2.\nChunk 4: 9 4 1 7.\nChunk 5: ya and i'm also looking for a modern european restaurant in the expensive price range um somewhere that's not in the north south of west of cambridge\nChunk 6: okay, then maybe somewhere that's like, um. ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, it's 3 1, 6, 0.", "role": "user", "streaming_reasoning": "The user mentions Yes, it's 3 1, 6, 0. It is not yet clear whether the user needs the full scope of the us...
{ "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 that for the same number of people at 9 pm on the same day. Key context: yes, it's 3 1, 6, 0; ya and i'm also looking for a modern european restau...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "MUL3259", "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_001230
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "um yes, i'm traveling to cambridge and i'm looking for information on local restaurants.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: um yes, i'm traveling to cambridge and i'm looking for information on local restaurants.", "dialogue_text": "Chunk 1: hello.\nChunk 2: um yes, i'm traveling to cambridge and i'm looking for information on local restaurants.", "instruction": "Help the user complete a spok...
{ "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 restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is searching for information on local restaurants. Key context: um yes, i'm traveling to cambridge and i'm looking for information on local restaurants. The answer should focus on the la...
{ "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": "MUL2369", "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_001231
train
audio
multi_turn
[ { "role": "user", "text": "yes, that'll be great. could you kindly help me book a table, please.", "turn_id": 1 }, { "role": "assistant", "text": "i would like to book for six people. on the first weekday of the coming week at 6 pm.", "turn_id": 2 }, { "role": "user", "text":...
{ "chunk_text": "Chunk 1: yes, that'll be great. could you kindly help me book a table, please.\nChunk 2: i would like to book for six people. on the first weekday of the coming week at 6 pm.\nChunk 3: yes, that's correct.\nChunk 4: my name is elizabeth gibson.\nChunk 5: sure, that's e l i z a b eth.\nChunk 6: gi bso...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, that'll be great. could you kindly help me book a table, please.", "role": "user", "streaming_reasoning": "The user mentions Yes, that'll be great. It is not yet cl...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is wanting to book table. Key context: yes, that'll be great; could you kindly help me book a table, please; i would like to book for six people; on the first weekday of the coming week at 6 pm....
{ "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": "SNG1476", "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_000366
train
audio
multi_turn
[ { "role": "user", "text": "Human: That is an interesting coincidence. The word \"malus\" means both apple and evil. So Eve actually ate evil.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: good point. Tom Brady is a true believer and a very spiritual person", "turn_id": 2 ...
{ "chunk_text": "Chunk 1: Human: That is an interesting coincidence. The word \"malus\" means both apple and evil. So Eve actually ate evil.\nChunk 2: Assistant: good point. Tom Brady is a true believer and a very spiritual person\nChunk 3: Human: I guess he would be sworn in on a Bible. Maybe his own. LOL.", "dial...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: That is an interesting coincidence. The word \"malus\" means both apple and evil. So Eve actually ate evil.", "role": "user", "streaming_reasoning": "The user men...
{ "answer": "Haha, he did write his own bible like book called \"athlete's bible\"", "reasoning": "Across the dialogue, the user discusses \"That is an interesting coincidence. The word \"malus\" means.\" over 3 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": "MultiDialog", "dialogue_id": "t_2bac601c-bf37-4338-9f83-6de3755484f8", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000043
train
audio
multi_turn
[ { "role": "user", "text": "I need to focus on work, but it's so noisy. Any suggestions?", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: I need to focus on work, but it's so noisy. Any suggestions?", "dialogue_text": "Chunk 1: I need to focus on work, but it's so noisy. Any suggestions?", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chunks.", "length...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "I need to focus on work, but it's so noisy. Any suggestions?", "role": "user", "streaming_reasoning": "The user mentions I need to focus on work, but it's so noisy. Any ...
{ "answer": "Noise-canceling headphones can be a real game-changer in noisy environments. Do you have a pair?", "reasoning": "Across the dialogue, the user is asking for recommendations about to focus on work. Key context: I need to focus on work, but it's so noisy; Any suggestions. The answer should focus on the l...
{ "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": "SD-Eval", "dialogue_id": "141_2", "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_001232
train
audio
multi_turn
[ { "role": "user", "text": "um yes, i'm looking for some information in cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "um i'm looking for a place to stay.", "turn_id": 2 }, { "role": "user", "text": "and i suppose it should include free wifi.", "turn_id": 3 ...
{ "chunk_text": "Chunk 1: um yes, i'm looking for some information in cambridge.\nChunk 2: um i'm looking for a place to stay.\nChunk 3: and i suppose it should include free wifi.\nChunk 4: yes, i i i suppose it should include free parking lot for me because we will drive.", "dialogue_text": "Chunk 1: um yes, i'm l...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um yes, i'm looking for some information in cambridge.", "role": "user", "streaming_reasoning": "The user mentions Um yes, i'm looking for some information in cambridge....
{ "answer": "Sure. I can help with the internet, parking; first I need to identify the right hotel option.", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: um yes, i'm looking for some information in cambridge; um i'm looking for a place to stay; and i suppose it...
{ "category": "information_extraction", "subcategory": "long_note_to_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": "MUL0070", "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_001233
train
audio
multi_turn
[ { "role": "user", "text": "yang.", "turn_id": 1 }, { "role": "assistant", "text": "uh, cambridge.", "turn_id": 2 }, { "role": "user", "text": "it will be pivot.", "turn_id": 3 }, { "role": "assistant", "text": "yes, on sunday also.", "turn_id": 4 }, { ...
{ "chunk_text": "Chunk 1: yang.\nChunk 2: uh, cambridge.\nChunk 3: it will be pivot.\nChunk 4: yes, on sunday also.\nChunk 5: oh. 8 2. 7, 9.\nChunk 6: 7, 6.\nChunk 7: 5, 4.\nChunk 8: double q.", "dialogue_text": "Chunk 1: yang.\nChunk 2: uh, cambridge.\nChunk 3: it will be pivot.\nChunk 4: yes, on sunday also.\nChu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yang.", "role": "user", "streaming_reasoning": "The user mentions Yang. It is not yet clear whether the user needs the full scope of the user's request. The assistant sh...
{ "answer": "I can help with the train. Could you share the departure, time?", "reasoning": "Across the dialogue, the user is talking about uh, cambridge. Key context: uh, cambridge; it will be pivot; yes, on sunday also. The answer should focus on the latest user turn while incorporating relevant context from earl...
{ "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": "MUL2886", "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_001234
train
audio
multi_turn
[ { "role": "user", "text": "if john langley speaking.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for a train. the train should departure from cameras. and you should go to transfer, uh.", "turn_id": 2 }, { "role": "user", "text": "it should arrive by 8 30 pm...
{ "chunk_text": "Chunk 1: if john langley speaking.\nChunk 2: i'm looking for a train. the train should departure from cameras. and you should go to transfer, uh.\nChunk 3: it should arrive by 8 30 pm should leave on monday.\nChunk 4: eat. okay.\nChunk 5: yes, i'm still here.\nChunk 6: okay, i'll book that one.\nChun...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "if john langley speaking.", "role": "user", "streaming_reasoning": "The user mentions If john langley speaking. It is not yet clear whether the user needs the full scope...
{ "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 train. Key context: if john langley speaking; i'm looking for a train; the train should departure from cameras; and you should go to transfer, uh....
{ "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": "MUL1847", "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_000367
train
audio
multi_turn
[ { "role": "user", "text": "Human: I guess it was innovative for its time. Now it just seems to normal and obvious. Well, I enjoyed chatting!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Me too. I am about to go read Tom Brady's book", "turn_id": 2 }, { "role": "us...
{ "chunk_text": "Chunk 1: Human: I guess it was innovative for its time. Now it just seems to normal and obvious. Well, I enjoyed chatting!\nChunk 2: Assistant: Me too. I am about to go read Tom Brady's book\nChunk 3: Human: Enjoy! Use it for your swearing in ceremony!", "dialogue_text": "Chunk 1: Human: I guess it...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I guess it was innovative for its time. Now it just seems to normal and obvious. Well, I enjoyed chatting!", "role": "user", "streaming_reasoning": "The user ment...
{ "answer": "lol I will", "reasoning": "Across the dialogue, the user is wanting to book human: enjoy. Key context: Human: I guess it was innovative for its time; Now it just seems to normal and obvious; Well, I enjoyed chatting; Assistant: Me too. The answer should focus on the latest user turn while incorporating...
{ "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": "MultiDialog", "dialogue_id": "t_2bac601c-bf37-4338-9f83-6de3755484f8", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001235
train
audio
multi_turn
[ { "role": "user", "text": "hi, i'm looking for a train.", "turn_id": 1 }, { "role": "assistant", "text": "the. i'd like to go to norwich. the train should arrive by 8 45.", "turn_id": 2 }, { "role": "user", "text": "the train should leave on tuesday.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: hi, i'm looking for a train.\nChunk 2: the. i'd like to go to norwich. the train should arrive by 8 45.\nChunk 3: the train should leave on tuesday.\nChunk 4: and to depart. from the legendary university.\nChunk 5: anything arriving by 8 45.\nChunk 6: um can i book for 7 people, please.\nChu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, i'm looking for a train.", "role": "user", "streaming_reasoning": "The user mentions Hi, i'm looking for a train. It is not yet clear whether the user needs the full...
{ "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 train. Key context: hi, i'm looking for a train; i'd like to go to norwich; the train should arrive by 8 45; the train should leave on tuesday. Th...
{ "category": "education", "subcategory": "course_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": "MUL3011", "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_000368
train
audio
multi_turn
[ { "role": "user", "text": "Human: I don't really know, it's hard to choose from the 300 registered heroes in the US.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: It is hard, my favorite is Batman though, I like Marvel comics better but Batman is Batman", "turn_id": 2 },...
{ "chunk_text": "Chunk 1: Human: I don't really know, it's hard to choose from the 300 registered heroes in the US.\nChunk 2: Assistant: It is hard, my favorite is Batman though, I like Marvel comics better but Batman is Batman\nChunk 3: Human: Well then you must know that batman and some others were created by stan ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I don't really know, it's hard to choose from the 300 registered heroes in the US.", "role": "user", "streaming_reasoning": "The user mentions talking about 300, ...
{ "answer": "They were really? Stan Lee was a master of comic books, real genius a lot of imagination", "reasoning": "Across the dialogue, the user discusses \"I don't really know, it's hard to choose from the 300.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversa...
{ "category": "creative_planning", "subcategory": "event_idea", "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_552a81c8-c15a-4c07-871e-955796f3741b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001236
train
audio
multi_turn
[ { "role": "user", "text": "yes. um, can you please, can you please give me the price range and the dress please of the restaurant.", "turn_id": 1 }, { "role": "assistant", "text": "yes, please.", "turn_id": 2 }, { "role": "user", "text": "oh, okay. thank you very much for tha...
{ "chunk_text": "Chunk 1: yes. um, can you please, can you please give me the price range and the dress please of the restaurant.\nChunk 2: yes, please.\nChunk 3: oh, okay. thank you very much for that.\nChunk 4: yes. um. can you please book a parking spot for me.\nChunk 5: okay. um, it's. s e 9 0.\nChunk 6: if i'm i...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes. um, can you please, can you please give me the price range and the dress please of the restaurant.", "role": "user", "streaming_reasoning": "The user mentions Yes. ...
{ "answer": "Sure. I can help with the pricerange, address; first I need to identify the right restaurant option.", "reasoning": "Across the dialogue, the user is wanting to book parking spot for me. Key context: um, can you please, can you please give me the price range and the dress please of the restaurant; yes,...
{ "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": "SNG0924", "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_001237
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a place to go in town and i wanted to be in the type of museum.", "turn_id": 2 }, { "role": "user", "text": "yes, thank you.", "turn_id": 3 }, { "role": "assis...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a place to go in town and i wanted to be in the type of museum.\nChunk 3: yes, thank you.\nChunk 4: okay, thank you. i wanted to know their post code, please.\nChunk 5: okay, great. and also i'm looking for a restaurant where they could serve some. uh, f...
{ "num_checkpoints": 5, "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 restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: yes, i'm looking for a place to go in town and i wanted to be in the type of museum; yes, thank you; okay, thank you; i wanted to know ...
{ "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": "MUL0484", "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_001238
train
audio
multi_turn
[ { "role": "user", "text": "yes, that's right.", "turn_id": 1 }, { "role": "assistant", "text": "and also, i suppose the hotel should be in the center and include free wi fi.", "turn_id": 2 }, { "role": "user", "text": "yes, and it should be in the moderate price range and. so...
{ "chunk_text": "Chunk 1: yes, that's right.\nChunk 2: and also, i suppose the hotel should be in the center and include free wi fi.\nChunk 3: yes, and it should be in the moderate price range and. so do you have any reservation.\nChunk 4: okay, thank you very much.\nChunk 5: oh, what's a pity, but it's it's quite ac...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, that's right.", "role": "user", "streaming_reasoning": "The user mentions Yes, that's right. It is not yet clear whether the user needs the full scope of the user's...
{ "answer": "I can help book that. Could you provide the day, stay_length, party_size?", "reasoning": "Across the dialogue, the user is talking about yes, that's right. Key context: yes, that's right; and also, i suppose the hotel should be in the center and include free wi fi; yes, and it should be in the moderate...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "MUL1136", "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_001239
train
audio
multi_turn
[ { "role": "user", "text": "so 1st of all, i am looking for a train plane.", "turn_id": 1 }, { "role": "assistant", "text": "birmingham new street.", "turn_id": 2 }, { "role": "user", "text": "uh, it should go through to cambridge, please.", "turn_id": 3 }, { "role...
{ "chunk_text": "Chunk 1: so 1st of all, i am looking for a train plane.\nChunk 2: birmingham new street.\nChunk 3: uh, it should go through to cambridge, please.\nChunk 4: i'd like to travel on wednesday, please.\nChunk 5: my loss. uh, meeting is at 5, um, so about 15 minutes after that, please.\nChunk 6: uh, yes, t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "so 1st of all, i am looking for a train plane.", "role": "user", "streaming_reasoning": "The user mentions So 1st of all, i am looking for a train plane. It is not yet c...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train plane. Key context: so 1st of all, i am looking for a train plane; birmingham new street; uh, it should go through to cambridge, please; i'd like to travel on wednesday, plea...
{ "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": "MUL2030", "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_001240
train
audio
multi_turn
[ { "role": "user", "text": "okay, i'd like to book a table case for the same group of seven people at 9 o'clock on the same day, tuesday.", "turn_id": 1 }, { "role": "assistant", "text": "yes, my name is dwayne.", "turn_id": 2 }, { "role": "user", "text": "yes, drain dwa.", ...
{ "chunk_text": "Chunk 1: okay, i'd like to book a table case for the same group of seven people at 9 o'clock on the same day, tuesday.\nChunk 2: yes, my name is dwayne.\nChunk 3: yes, drain dwa.\nChunk 4: y n e.\nChunk 5: yes, darling d a r l.\nChunk 6: a nd.\nChunk 7: yeah.\nChunk 8: no, no, no, no, that's fine. th...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, i'd like to book a table case for the same group of seven people at 9 o'clock on the same day, tuesday.", "role": "user", "streaming_reasoning": "The user mentions...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is wanting to book table case for the same group of seven people at 9 o'clock on the same day. Key context: okay, i'd like to book a table case for the same group of seven people at 9 o'clock on...
{ "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": "MUL2053", "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_000369
train
audio
multi_turn
[ { "role": "user", "text": "Human: Me either, I also didnt realize there were so many different types of Jazz", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes! Since the 1920s Jazz Age, jazz has become recognized as a major form of musical expression.", "turn_id": 2 }, ...
{ "chunk_text": "Chunk 1: Human: Me either, I also didnt realize there were so many different types of Jazz\nChunk 2: Assistant: Yes! Since the 1920s Jazz Age, jazz has become recognized as a major form of musical expression.\nChunk 3: Human: So any plans for christmas?", "dialogue_text": "Chunk 1: Human: Me either...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Me either, I also didnt realize there were so many different types of Jazz", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Jazz. ...
{ "answer": "Just giving gifts to family. I got my brother some new shirts. I can't believe the plain grey shirt mark zuckerburg wears all the time costs between $300 and $400", "reasoning": "Across the dialogue, the user discusses \"Me either, I also didnt realize there were so many.\" over 3 turns. The answer sho...
{ "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_19e6b5a2-2ad2-46d7-a1f0-44c995b3fad1", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001241
train
audio
multi_turn
[ { "role": "user", "text": "if i want to make a book, please recommend for me.", "turn_id": 1 }, { "role": "assistant", "text": "a book or the same group of people.", "turn_id": 2 }, { "role": "user", "text": "yes, 5 people.", "turn_id": 3 }, { "role": "assistant",...
{ "chunk_text": "Chunk 1: if i want to make a book, please recommend for me.\nChunk 2: a book or the same group of people.\nChunk 3: yes, 5 people.\nChunk 4: ok, i will choose this one.\nChunk 5: it's tonight.\nChunk 6: it's, uh, about saturday.\nChunk 7: okay, thank you.\nChunk 8: okay, fine. oh, then how about birt...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "if i want to make a book, please recommend for me.", "role": "user", "streaming_reasoning": "The user mentions If i want to make a book, please recommend for me. It is n...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book or the same group of people. Key context: if i want to make a book, please recommend for me; a book or the same group of people; yes, 5 people; ok, i will choose this on...
{ "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": "MUL3932", "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_001242
train
audio
multi_turn
[ { "role": "user", "text": "okay, you don't have one with a star of five.", "turn_id": 1 }, { "role": "assistant", "text": "okay. how about one that has a star of four.", "turn_id": 2 }, { "role": "user", "text": "okay, that should be fine. can i make a booking for four people...
{ "chunk_text": "Chunk 1: okay, you don't have one with a star of five.\nChunk 2: okay. how about one that has a star of four.\nChunk 3: okay, that should be fine. can i make a booking for four people.\nChunk 4: i'm starting from wednesday for two nights.\nChunk 5: my name is ronald peanut.\nChunk 6: yes, i can recei...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, you don't have one with a star of five.", "role": "user", "streaming_reasoning": "The user mentions Okay, you don't have one with a star of five. It is not yet cle...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book okay, you don't have one with a star of five. Key context: okay, you don't have one with a star of five; how about one that has a star of four; okay, that should be fine...
{ "category": "daily_life", "subcategory": "shopping_decision", "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": "SNG1598", "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_001243
train
audio
multi_turn
[ { "role": "user", "text": "right. lovely. and what time does it arrive in cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "and then lastly. what is the travel time between the two stations, please.", "turn_id": 2 }, { "role": "user", "text": "all right, okay, that...
{ "chunk_text": "Chunk 1: right. lovely. and what time does it arrive in cambridge.\nChunk 2: and then lastly. what is the travel time between the two stations, please.\nChunk 3: all right, okay, that's perfect. thanks for that.\nChunk 4: uh, also just what is that train id.\nChunk 5: pr 2 2 8 6 perfect.\nChunk 6: mh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "right. lovely. and what time does it arrive in cambridge.", "role": "user", "streaming_reasoning": "The user mentions Right. lovely. and what time does it arrive in camb...
{ "answer": "I can help with the restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: and what time does it arrive in cambridge; and then lastly; what is the travel time between the two stations, please; all right, okay, that's pe...
{ "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": "MUL2030", "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_001244
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.", "dialogue_text": "Chunk 1: good morning. how are you.\nChunk 2: oh, i'm doing great. thank you.\nChunk 3: i am lo...
{ "num_checkpoints": 4, "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": "I can help with the attraction. Could you share the area, type?", "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 latest user turn while ...
{ "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_001245
train
audio
multi_turn
[ { "role": "user", "text": "the train should go to bishop. torture and should arrive by 10 have a lot of the way, not one so three hours from.", "turn_id": 1 }, { "role": "assistant", "text": "do you think.", "turn_id": 2 }, { "role": "user", "text": "yeah, that's fine. do you...
{ "chunk_text": "Chunk 1: the train should go to bishop. torture and should arrive by 10 have a lot of the way, not one so three hours from.\nChunk 2: do you think.\nChunk 3: yeah, that's fine. do you have a train id for me.\nChunk 4: okay, perfect. i will try for a ticket.\nChunk 5: okay. and what is the departure t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "the train should go to bishop. torture and should arrive by 10 have a lot of the way, not one so three hours from.", "role": "user", "streaming_reasoning": "The user men...
{ "answer": "I can help with the hotel. Could you share the area, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay the place i'm looking for should be like a distant engine yourself. Key context: the train should go to bishop; torture and should arrive by 10 have a lot of the...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "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": "MUL2690", "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_001246
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is lola redwood.", "turn_id": 1 }, { "role": "assistant", "text": "hi, my noisy. i'm looking for information in cambridge about a particular restaurant.", "turn_id": 2 }, { "role": "user", "text": "yes, when i was looking for a restauran...
{ "chunk_text": "Chunk 1: hi, my name is lola redwood.\nChunk 2: hi, my noisy. i'm looking for information in cambridge about a particular restaurant.\nChunk 3: yes, when i was looking for a restaurant called the curry gardens.\nChunk 4: only the phone number in the area of supplies for now.\nChunk 5: oh, come again....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is lola redwood.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is lola redwood. It is not yet clear whether the user needs the full...
{ "answer": "I can help with the attraction. Could you share the area, type?", "reasoning": "Across the dialogue, the user is searching for information in cambridge about a particular restaurant. Key context: hi, my name is lola redwood; hi, my noisy; i'm looking for information in cambridge about a particular rest...
{ "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": "MUL2729", "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_000370
train
audio
multi_turn
[ { "role": "user", "text": "Human: They are usually a pretty good home team. They have a tear jerking tradition where they wave to the cancer hospital for kids after the 3rd quarter.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Hey, that's great! The kids must love that sort o...
{ "chunk_text": "Chunk 1: Human: They are usually a pretty good home team. They have a tear jerking tradition where they wave to the cancer hospital for kids after the 3rd quarter.\nChunk 2: Assistant: Hey, that's great! The kids must love that sort of thing. So much money goes to football. The highest paid across al...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: They are usually a pretty good home team. They have a tear jerking tradition where they wave to the cancer hospital for kids after the 3rd quarter.", "role": "user", ...
{ "answer": "I guess, but that was back in 1916. What a game. I wonder who scheduled that one.", "reasoning": "Across the dialogue, the user is asking for help with human: they are usually a pretty good home team. Key context: Human: They are usually a pretty good home team; They have a tear jerking tradition where...
{ "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_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_001247
train
audio
multi_turn
[ { "role": "user", "text": "oh. good afternoon. hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, ma'am, i'm looking for a place to dine, please.", "turn_id": 2 }, { "role": "user", "text": "uh, the place should be in the center. this.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: oh. good afternoon. hello.\nChunk 2: yes, ma'am, i'm looking for a place to dine, please.\nChunk 3: uh, the place should be in the center. this.\nChunk 4: yes, the restaurant should be in the expensive price range.\nChunk 5: and the restaurant should serve gourmet comfort food.\nChunk 6: yes...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "oh. good afternoon. hello.", "role": "user", "streaming_reasoning": "The user mentions Oh. good afternoon. hello. It is not yet clear whether the user needs the full sco...
{ "answer": "Sure. I can provide the postcode for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: good afternoon; yes, ma'am, i'm looking for a place to dine, please; uh, the place should be in the center; yes, the restaurant should be in th...
{ "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": "SNG1592", "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_001248
train
audio
multi_turn
[ { "role": "user", "text": "thank you. thank you.", "turn_id": 1 }, { "role": "assistant", "text": "oh. oh, okay. that's disappointing. how about something that serves vietnamese food.", "turn_id": 2 }, { "role": "user", "text": "ok, thank you.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: thank you. thank you.\nChunk 2: oh. oh, okay. that's disappointing. how about something that serves vietnamese food.\nChunk 3: ok, thank you.\nChunk 4: yes, that would be fine. please, can you make a booking for a table at 5 four times the same day, which is sunday.\nChunk 5: okay.\nChunk 6:...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "thank you. thank you.", "role": "user", "streaming_reasoning": "The user mentions Thank you. thank you. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help book that. Could you provide the area, price?", "reasoning": "Across the dialogue, the user is wanting to book that's disappointing. Key context: that's disappointing; how about something that serves vietnamese food; ok, thank you; yes, that would be fine. The answer should focus on the late...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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": "MUL2065", "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_001249
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is heather overy.", "turn_id": 1 }, { "role": "assistant", "text": "hi, my name's i'm looking for places to visit in.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a place where i can direct some of the multiple sports. an...
{ "chunk_text": "Chunk 1: hi, my name is heather overy.\nChunk 2: hi, my name's i'm looking for places to visit in.\nChunk 3: i'm looking for a place where i can direct some of the multiple sports. and it will be at the end of the town.\nChunk 4: yes, my mother.\nChunk 5: find the one that is in the form of a museum....
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is heather overy.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is heather overy. It is not yet clear whether the user needs the fu...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for places to visit in. Key context: hi, my name is heather overy; hi, my name's i'm looking for places to visit in; i'm looking for a place where i can direct some of the multipl...
{ "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": "SNG1647", "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_001250
train
audio
multi_turn
[ { "role": "user", "text": "okay, it's 5 to 2. did you get that.", "turn_id": 1 }, { "role": "assistant", "text": "5 9 1 did you get it.", "turn_id": 2 }, { "role": "user", "text": "and lastly, 4 2, 3, 8.", "turn_id": 3 }, { "role": "assistant", "text": "okay, ...
{ "chunk_text": "Chunk 1: okay, it's 5 to 2. did you get that.\nChunk 2: 5 9 1 did you get it.\nChunk 3: and lastly, 4 2, 3, 8.\nChunk 4: okay, thank you. i also want to book in a four star b and b with the free wi fi.\nChunk 5: okay, how can you please book for one person.\nChunk 6: uh, on friday.\nChunk 7: for two ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, it's 5 to 2. did you get that.", "role": "user", "streaming_reasoning": "The user mentions Okay, it's 5 to 2. did you get that. 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 wanting to book in a four star b. Key context: okay, it's 5 to 2; did you get that; 5 9 1 did you get it; and lastly, 4 2, 3, 8. The answer should focus on the ...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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": "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_001251
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "okay thank you um i would like to book some tickets for a train that is committing on tuesday from cambridge to leicester and it should live", "turn_id": 2 }, { "role": "user", "t...
{ "chunk_text": "Chunk 1: hello, how are you.\nChunk 2: okay thank you um i would like to book some tickets for a train that is committing on tuesday from cambridge to leicester and it should live\nChunk 3: alright, i like to book for for my cousins and myself.\nChunk 4: yes. uh, it's 6 8, 7, 7.\nChunk 5: 4 5 9 2.\nC...
{ "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": "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 tickets for a train that is committing on tuesday from cambridge to leicester. Key context: hello, how are you; okay thank you um i would like t...
{ "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": "MUL0374", "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_001252
train
audio
multi_turn
[ { "role": "user", "text": "alright, so i would like to book for five people on tuesday at 11:15 a m.", "turn_id": 1 }, { "role": "assistant", "text": "alright thank you uh luckily i would like to book a teddy to commit me from the hotel to the restaurant and it should arrive", "turn_id":...
{ "chunk_text": "Chunk 1: alright, so i would like to book for five people on tuesday at 11:15 a m.\nChunk 2: alright thank you uh luckily i would like to book a teddy to commit me from the hotel to the restaurant and it should arrive\nChunk 3: by 1115 a m\nChunk 4: okay, my number is 5 1.\nChunk 5: 8 9 3.\nChunk 6: ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "alright, so i would like to book for five people on tuesday at 11:15 a m.", "role": "user", "streaming_reasoning": "The user mentions wanting to book 11:15, Alright. It ...
{ "answer": "Sure. I can provide the car for the matching taxi option.", "reasoning": "Across the dialogue, the user is wanting to book for five people on tuesday at 11:15 a m. Key context: alright, so i would like to book for five people on tuesday at 11:15 a m; alright thank you uh luckily i would like to book a ...
{ "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": "MUL1962", "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_000371
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah. Did you know there is a negative correlation between the IQ and chess skills?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Really? I would have thought you needed to be pretty smart to play chess! But maybe not since pawns no longer hav...
{ "chunk_text": "Chunk 1: Human: Yeah. Did you know there is a negative correlation between the IQ and chess skills?\nChunk 2: Assistant: 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\nChunk 3: Human: Yeah. I guess ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah. Did you know there is a negative correlation between the IQ and chess skills?", "role": "user", "streaming_reasoning": "The user mentions talking about Huma...
{ "answer": "India I believe - and it became more modern in Spain in the 1400s", "reasoning": "Across the dialogue, the user is asking for help with human: yeah. Key context: Human: Yeah; Did you know there is a negative correlation between the IQ and chess skills; Assistant: Really; I would have thought you needed...
{ "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_001253
train
audio
multi_turn
[ { "role": "user", "text": "an iphone is abc. ui n.", "turn_id": 1 }, { "role": "assistant", "text": "and i would like to book for four nights and five days starting from friday.", "turn_id": 2 }, { "role": "user", "text": "i'm lucky. how about 39 things.", "turn_id": 3 ...
{ "chunk_text": "Chunk 1: an iphone is abc. ui n.\nChunk 2: and i would like to book for four nights and five days starting from friday.\nChunk 3: i'm lucky. how about 39 things.\nChunk 4: i'm also looking for a train.\nChunk 5: and the train should leave after 8 pm on the same day of the hotel bk.\nChunk 6: ministry...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "an iphone is abc. ui n.", "role": "user", "streaming_reasoning": "The user mentions An iphone is abc. ui n. It is not yet clear whether the user needs the full scope of ...
{ "answer": "Sure. I can provide the id, ticket for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train. Key context: an iphone is abc; and i would like to book for four nights and five days starting from friday; how about 39 things; i'm also looking for a train. The answ...
{ "category": "daily_life", "subcategory": "shopping_decision", "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": "MUL2646", "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_001254
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i messaged a test in my favors.", "turn_id": 2 }, { "role": "user", "text": "it's betty de la.", "turn_id": 3 }, { "role": "assistant", "text": "i'm looking for a place to stay...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i messaged a test in my favors.\nChunk 3: it's betty de la.\nChunk 4: i'm looking for a place to stay. it should be in the cheap price range.\nChunk 5: and i. a place to die and i made time.", "dialogue_text": "Chunk 1: hello.\nChunk 2: i messaged a test in my favors.\nChu...
{ "num_checkpoints": 5, "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 restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: i messaged a test in my favors; it's betty de la; i'm looking for a place to stay; it should be in the cheap price range. The answer should f...
{ "category": "daily_life", "subcategory": "shopping_decision", "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": "MUL3506", "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_000372
train
audio
multi_turn
[ { "role": "user", "text": "Human: Are you able to run and do carries like adrian peterson?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah, in my dreams. Did you know that only two African-American QBs have won the Superbowl. Too bad Warren Moon didn't.", "turn_id": 2 ...
{ "chunk_text": "Chunk 1: Human: Are you able to run and do carries like adrian peterson?\nChunk 2: Assistant: Yeah, in my dreams. Did you know that only two African-American QBs have won the Superbowl. Too bad Warren Moon didn't.\nChunk 3: Human: there also seems to be more records being broken every year... especia...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Are you able to run and do carries like adrian peterson?", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not yet clear whet...
{ "answer": "Yeah. I wonder in Homer Simpson has a record for having 188 jobs in 400 episodes?", "reasoning": "Across the dialogue, the user discusses \"Are you able to run and do carries like adrian.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.",...
{ "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_5cf29dac-f886-4bc8-928d-a22dbdebe909", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001255
train
audio
multi_turn
[ { "role": "user", "text": "um go that may i know the post code of the restaurant.", "turn_id": 1 }, { "role": "assistant", "text": "got it. may i know the address.", "turn_id": 2 }, { "role": "user", "text": "hmm, got that. thank you.", "turn_id": 3 }, { "role": "...
{ "chunk_text": "Chunk 1: um go that may i know the post code of the restaurant.\nChunk 2: got it. may i know the address.\nChunk 3: hmm, got that. thank you.\nChunk 4: sure, i was looking for a train.\nChunk 5: um i think the trend should live on this monday.\nChunk 6: right monday.\nChunk 7: and should depart from....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um go that may i know the post code of the restaurant.", "role": "user", "streaming_reasoning": "The user mentions Um go that may i know the post code of the restaurant....
{ "answer": "I can help with the train. Could you share the day, time?", "reasoning": "Across the dialogue, the user is searching for train. Key context: um go that may i know the post code of the restaurant; may i know the address; hmm, got that; sure, i was looking for a train. The answer should focus on the late...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "MUL0315", "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_000373
train
audio
multi_turn
[ { "role": "user", "text": "Human: I love football both college and NFL, do you have a favorite NFL team of the 32?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I'm a New England Patriots fan and huge fan of Tom Brady how about you?", "turn_id": 2 }, { "role": "use...
{ "chunk_text": "Chunk 1: Human: I love football both college and NFL, do you have a favorite NFL team of the 32?\nChunk 2: Assistant: I'm a New England Patriots fan and huge fan of Tom Brady how about you?\nChunk 3: Human: Nice I am a Vikings fan, not doing so hot as of late. I also like the University of Iowa Hawke...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I love football both college and NFL, do you have a favorite NFL team of the 32?", "role": "user", "streaming_reasoning": "The user mentions talking about 32, Hum...
{ "answer": "No I didn't know this. Did you know that in the 60's top bowlers made twice as much as the top football players?", "reasoning": "Across the dialogue, the user is asking for help with human: i love football both college and nfl, do you have a favorite nfl team of the 32. Key context: Human: I love footb...
{ "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_3feaeda2-e37a-4e0f-8762-29eb67352dbd", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000374
train
audio
multi_turn
[ { "role": "user", "text": "Human: Same here! And, while on the subject of birds, I recently learned that all birds have wings except for the extinct moa and elephant birds. I wonder how they are even considered birds since they", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Ver...
{ "chunk_text": "Chunk 1: Human: Same here! And, while on the subject of birds, I recently learned that all birds have wings except for the extinct moa and elephant birds. I wonder how they are even considered birds since they do not have wings? Strange!\nChunk 2: Assistant: Very strange! I also wonder how they class...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Same here! And, while on the subject of birds, I recently learned that all birds have wings except for the extinct moa and elephant birds. I wonder how they are even consider...
{ "answer": "I am not either. do you plan on watching the oscars.", "reasoning": "Across the dialogue, the user is asking for help with human: same here. Key context: Human: Same here; And, while on the subject of birds, I recently learned that all birds have wings except for the extinct moa and elephant birds; I w...
{ "category": "education", "subcategory": "course_planning", "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_15b965a8-ac24-46d6-bec6-ebcfb8373bf9", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001256
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello, am i said it's a customer sale.", "turn_id": 1 }, { "role": "assistant", "text": "if john langley speaking.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train. the train should departure from cameras. and you should g...
{ "chunk_text": "Chunk 1: hello. hello, am i said it's a customer sale.\nChunk 2: if john langley speaking.\nChunk 3: i'm looking for a train. the train should departure from cameras. and you should go to transfer, uh.\nChunk 4: it should arrive by 8 30 pm should leave on monday.\nChunk 5: eat. okay.\nChunk 6: yes, i...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello, am i said it's a customer sale.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello, am i said it's a customer sale. It is not yet cle...
{ "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, am i said it's a customer sale; if john langley speaking; i'm looking for a train; the train should departure from cameras. The answer should focus on th...
{ "category": "finance_consumer", "subcategory": "budget_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": "MUL1847", "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_001257
train
audio
multi_turn
[ { "role": "user", "text": "hello is this customer service center.", "turn_id": 1 }, { "role": "assistant", "text": "uh, yes, i'm looking for a restaurant. can you give me some advice.", "turn_id": 2 }, { "role": "user", "text": "yes, i hope the restaurant is in the source.", ...
{ "chunk_text": "Chunk 1: hello is this customer service center.\nChunk 2: uh, yes, i'm looking for a restaurant. can you give me some advice.\nChunk 3: yes, i hope the restaurant is in the source.", "dialogue_text": "Chunk 1: hello is this customer service center.\nChunk 2: uh, yes, i'm looking for a restaurant. c...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello is this customer service center.", "role": "user", "streaming_reasoning": "The user mentions Hello is this customer service center. It is not yet clear whether the...
{ "answer": "I can help with the restaurant. Could you share the food, price?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: hello is this customer service center; uh, yes, i'm looking for a restaurant; can you give me some advice; yes, i hope the restaurant is in the source...
{ "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": "SNG0758", "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_001258
train
audio
multi_turn
[ { "role": "user", "text": "find this four star hotel that include free wi fi and free parking", "turn_id": 1 }, { "role": "assistant", "text": "okay this sounds good then please help me to book ah for four people and from tomorrow and the day after tomorrow starting for monday thank you", ...
{ "chunk_text": "Chunk 1: find this four star hotel that include free wi fi and free parking\nChunk 2: okay this sounds good then please help me to book ah for four people and from tomorrow and the day after tomorrow starting for monday thank you\nChunk 3: yes, correct.\nChunk 4: well, then let's do saturday.\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "find this four star hotel that include free wi fi and free parking", "role": "user", "streaming_reasoning": "The user mentions searching for Find. It is not yet clear wh...
{ "answer": "I can help book that. Could you provide the departure, destination?", "reasoning": "Across the dialogue, the user is searching for ah for four people. Key context: well, then let's do saturday; can see again; uh yes uh my name is joseph smith it's j o s e p h i for josephine and s m i t h for smith wel...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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": "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_001259
train
audio
multi_turn
[ { "role": "user", "text": "r a p e.", "turn_id": 1 }, { "role": "assistant", "text": "r y.", "turn_id": 2 }, { "role": "user", "text": "1 8 2.", "turn_id": 3 }, { "role": "assistant", "text": "it was melt dot com.", "turn_id": 4 }, { "role": "user"...
{ "chunk_text": "Chunk 1: r a p e.\nChunk 2: r y.\nChunk 3: 1 8 2.\nChunk 4: it was melt dot com.\nChunk 5: alright.\nChunk 6: okay.\nChunk 7: 6 15, 1 80, okay.\nChunk 8: 7 7, 6 6 ok.", "dialogue_text": "Chunk 1: r a p e.\nChunk 2: r y.\nChunk 3: 1 8 2.\nChunk 4: it was melt dot com.\nChunk 5: alright.\nChunk 6: ok...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "r a p e.", "role": "user", "streaming_reasoning": "The user mentions R a p e. It is not yet clear whether the user needs the full scope of the user's request. The assist...
{ "answer": "I can help with the restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is talking about it was melt dot com. Key context: it was melt dot com; 6 15, 1 80, okay; 7 7, 6 6 ok. The answer should focus on the latest user turn while incorporating relevant contex...
{ "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": "SNG0361", "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_000375
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah, thats a long cat nap for sure!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Absolutely! There are cat cafes n Japan and Taiwan where people can pay hourly to play with cat and have drinks. I'd like to see some of those where I live!", ...
{ "chunk_text": "Chunk 1: Human: Yeah, thats a long cat nap for sure!\nChunk 2: Assistant: Absolutely! There are cat cafes n Japan and Taiwan where people can pay hourly to play with cat and have drinks. I'd like to see some of those where I live!\nChunk 3: Human: Me too,l i have been to Japan and never saw them!", ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah, thats a long cat nap for sure!", "role": "user", "streaming_reasoning": "The user mentions Human: Yeah, thats a long cat nap for sure!. It is not yet clear ...
{ "answer": "Oh really? I'd love to visit Japan! They have such a neat culture!", "reasoning": "Across the dialogue, the user is asking for help with human: yeah, thats a long cat nap for sure. Key context: Human: Yeah, thats a long cat nap for sure; Assistant: Absolutely; There are cat cafes n Japan and Taiwan whe...
{ "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_6c02f06c-0cf6-4906-8ff6-eb23afbedf78", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001260
train
audio
multi_turn
[ { "role": "user", "text": "uh, i'm looking for a place to go in cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "ah i want to visit a college in cambridge.", "turn_id": 2 }, { "role": "user", "text": "i prefer to be in the west of cambridge.", "turn_id": 3 }...
{ "chunk_text": "Chunk 1: uh, i'm looking for a place to go in cambridge.\nChunk 2: ah i want to visit a college in cambridge.\nChunk 3: i prefer to be in the west of cambridge.\nChunk 4: mm. okay. may i know the address of this watch.\nChunk 5: so it's great. and how about the phone number of this church.\nChunk 6: ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, i'm looking for a place to go in cambridge.", "role": "user", "streaming_reasoning": "The user mentions Uh, i'm looking for a place to go in cambridge. It is not yet...
{ "answer": "Sure. I can provide the address, phone, postcode for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for place to go in cambridge. Key context: uh, i'm looking for a place to go in cambridge; ah i want to visit a college in cambridge; i prefer to be in the wes...
{ "category": "education", "subcategory": "course_planning", "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": "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_001261
train
audio
multi_turn
[ { "role": "user", "text": "e ll o.", "turn_id": 1 }, { "role": "assistant", "text": "ok.", "turn_id": 2 }, { "role": "user", "text": "okay. um, i also am looking to attend a local attraction located downtown.", "turn_id": 3 }, { "role": "assistant", "text": "o...
{ "chunk_text": "Chunk 1: e ll o.\nChunk 2: ok.\nChunk 3: okay. um, i also am looking to attend a local attraction located downtown.\nChunk 4: oh, okay. do you have the phone number for that.\nChunk 5: and the address.\nChunk 6: okay, and the post code.\nChunk 7: okay, thank you.\nChunk 8: yes, please.", "dialogue_...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "e ll o.", "role": "user", "streaming_reasoning": "The user mentions E ll o. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "Sure. I can provide the phone, address, postcode for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for um, i also am looking to attend a local attraction located downtown. Key context: um, i also am looking to attend a local attraction located downtown; do y...
{ "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": "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_spokenwoz_v02_001262
train
audio
multi_turn
[ { "role": "user", "text": "oh, that sounds good.", "turn_id": 1 }, { "role": "assistant", "text": "yes, just for myself. one person.", "turn_id": 2 }, { "role": "user", "text": "yes, it is one o nine. four, two, five. eight, five. six. zero seven nine one. four, four. set.", ...
{ "chunk_text": "Chunk 1: oh, that sounds good.\nChunk 2: yes, just for myself. one person.\nChunk 3: yes, it is one o nine. four, two, five. eight, five. six. zero seven nine one. four, four. set.\nChunk 4: yeah i'm looking for a place to dine i think i'd like to know nothing too too expensive maybe bridge mid range...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "oh, that sounds good.", "role": "user", "streaming_reasoning": "The user mentions Oh, that sounds good. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "Sure. I can provide the phone for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for oh, that sounds good. Key context: oh, that sounds good; yes, just for myself; yes, it is one o nine; four, two, five. The answer should focus on the latest user turn while i...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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": "MUL4028", "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_000376
train
audio
multi_turn
[ { "role": "user", "text": "Human: Hi, how are you? How much do you know about the Bible?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: yes I do. It the best selling book of all time", "turn_id": 2 }, { "role": "user", "text": "Human: Did you know that before 19...
{ "chunk_text": "Chunk 1: Human: Hi, how are you? How much do you know about the Bible?\nChunk 2: Assistant: yes I do. It the best selling book of all time\nChunk 3: Human: Did you know that before 1963, it was not uncommon for American students to be required to read from the Bible as part of their elementary educat...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Hi, how are you? How much do you know about the Bible?", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Bible. It is not yet clear...
{ "answer": "My mom told me that. Thomas jefferson did not believe in miracles and the resurrection.", "reasoning": "Across the dialogue, the user is wanting to book of all time human: did you know that before 1963. Key context: Human: Hi, how are you; How much do you know about the Bible; Assistant: yes I do; It t...
{ "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_2bac601c-bf37-4338-9f83-6de3755484f8", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001263
train
audio
multi_turn
[ { "role": "user", "text": "okay, sounds great.", "turn_id": 1 }, { "role": "assistant", "text": "thank you so much.", "turn_id": 2 }, { "role": "user", "text": "okay. do you have their phone number.", "turn_id": 3 }, { "role": "assistant", "text": "okay. could...
{ "chunk_text": "Chunk 1: okay, sounds great.\nChunk 2: thank you so much.\nChunk 3: okay. do you have their phone number.\nChunk 4: okay. could you please repeat that for me.\nChunk 5: okay, i'm running down. thank you.\nChunk 6: i don't think i need a booking right now.\nChunk 7: uh, does the restaurant will receiv...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, sounds great.", "role": "user", "streaming_reasoning": "The user mentions Okay, sounds great. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "Sure. I can help with the phone; first I need to identify the right restaurant option.", "reasoning": "Across the dialogue, the user is wanting to book booking right now. Key context: okay, sounds great; thank you so much; do you have their phone number; could you please repeat that for me. The answer ...
{ "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": "MUL3864", "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_001264
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 } ]
{ "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.", "dialogue_text": "Chunk 1: hello hello. hello. hello.\nChunk 2: hi, i'm planning a trip to cambridge. i'm lookin...
{ "num_checkpoints": 2, "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": "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: 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 your wonderful colle...
{ "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": "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_multidialog_v02_000377
train
audio
multi_turn
[ { "role": "user", "text": "Human: What? Really? That's insane! But then again I work on designing quantum computers so I've seen some weird stuff myself haha. Physics is weird in general, don't you think?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: You work on quantum comput...
{ "chunk_text": "Chunk 1: Human: What? Really? That's insane! But then again I work on designing quantum computers so I've seen some weird stuff myself haha. Physics is weird in general, don't you think?\nChunk 2: Assistant: You work on quantum computers?? For real? That is awesome! But yeah, physics is pretty weird....
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: What? Really? That's insane! But then again I work on designing quantum computers so I've seen some weird stuff myself haha. Physics is weird in general, don't you think?", ...
{ "answer": "Depends on the high school student, I guess. I couldn't really see writing 15 pages on about anything these days. LOL.", "reasoning": "Across the dialogue, the user is asking for help with writing 15 page. Key context: Human: What; That's insane; But then again I work on designing quantum computers so ...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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_9e641a59-4f10-4bd4-806e-2d3eee3dd423", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001265
train
audio
multi_turn
[ { "role": "user", "text": "hi, hello. hi, hello.", "turn_id": 1 }, { "role": "assistant", "text": "good in yourself.", "turn_id": 2 }, { "role": "user", "text": "i need your assistance. i'm looking for a place to stay.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: hi, hello. hi, hello.\nChunk 2: good in yourself.\nChunk 3: i need your assistance. i'm looking for a place to stay.\nChunk 4: so i'm looking for like a hotel that should be in the north and should be a type of guesthouse and should have a four\nChunk 5: star rating including free wi fi\nChu...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, hello. hi, hello.", "role": "user", "streaming_reasoning": "The user mentions Hi, hello. hi, hello. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help book that. Could you provide the price?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: good in yourself; i need your assistance; i'm looking for a place to stay; so i'm looking for like a hotel that should be in the north and should be a type of gu...
{ "category": "daily_life", "subcategory": "home_task", "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": "SNG0951", "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_001266
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm saying things to yourself.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "the train should go to ca...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm saying things to yourself.\nChunk 3: i'm looking for a train.\nChunk 4: the train should go to cambridge, departing from eli. that's e l y.\nChunk 5: uh, for tomorrow it's friday.\nChunk 6: anytime after should leave anytime after 2 30 in the afternoon.\nChunk 7: from ca...
{ "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 find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: i'm saying things to yourself; i'm looking for a train; the train should go to cambridge, departing from eli; that's e l y. The answer should focus on the lates...
{ "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": "MUL3562", "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_001267
train
audio
multi_turn
[ { "role": "user", "text": "perfect thank you so much for that i'm also looking for information on places that i can stay while in cambridge is this also something", "turn_id": 1 }, { "role": "assistant", "text": "that you can help me with", "turn_id": 2 }, { "role": "user", "...
{ "chunk_text": "Chunk 1: perfect thank you so much for that i'm also looking for information on places that i can stay while in cambridge is this also something\nChunk 2: that you can help me with\nChunk 3: okay so i'm looking for a place or a hotel that's located in an area where i have is of access to everywhere e...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "perfect thank you so much for that i'm also looking for information on places that i can stay while in cambridge is this also something", "role": "user", "streaming_reas...
{ "answer": "I can help book that. Could you provide the hotel_type?", "reasoning": "Across the dialogue, the user is searching for how about for one night. Key context: how about for one night; um, can you please tell me what day you have available. The answer should focus on the latest user turn while incorporati...
{ "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": "MUL2185", "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_001268
train
audio
multi_turn
[ { "role": "user", "text": "hello, i would like to plan a trip in cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "i would like to go in place in town.", "turn_id": 2 }, { "role": "user", "text": "a museum.", "turn_id": 3 }, { "role": "assistant", "...
{ "chunk_text": "Chunk 1: hello, i would like to plan a trip in cambridge.\nChunk 2: i would like to go in place in town.\nChunk 3: a museum.\nChunk 4: yes, please. can they get the phone number.", "dialogue_text": "Chunk 1: hello, i would like to plan a trip in cambridge.\nChunk 2: i would like to go in place in t...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, i would like to plan a trip in cambridge.", "role": "user", "streaming_reasoning": "The user mentions Hello, i would like to plan a trip in cambridge. It is not y...
{ "answer": "Sure. I can provide the phone for the matching attraction option.", "reasoning": "Across the dialogue, the user discusses \"hello, i would like to plan a trip in.\" over 4 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning...
{ "category": "creative_planning", "subcategory": "event_idea", "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": "MUL3072", "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_001269
train
audio
multi_turn
[ { "role": "user", "text": "hello, can you hear me.", "turn_id": 1 }, { "role": "assistant", "text": "yes i'm looking for a hotel to stay overnight um it should have a star of a including free parking in the east of the city please", "turn_id": 2 }, { "role": "user", "text": "...
{ "chunk_text": "Chunk 1: hello, can you hear me.\nChunk 2: yes i'm looking for a hotel to stay overnight um it should have a star of a including free parking in the east of the city please\nChunk 3: great sounds great yes i do need a reservation i need two double rooms and i'll stay there from wednesday and leave on...
{ "num_checkpoints": 5, "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 book that. Could you provide the price, hotel_type, stay_length?", "reasoning": "Across the dialogue, the user is searching for reservation i need two double rooms. Key context: hello, can you hear me; that's all i need; oh, too bad; but i think i can accept that. The answer should focus on ...
{ "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": "MUL0949", "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_000378
train
audio
multi_turn
[ { "role": "user", "text": "Human: that's nuts to me. I wonder if he was nominated?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: i dont think so but im not for sure on that. the oscars are the oldest worldwide entertainment award show", "turn_id": 2 }, { "role": "u...
{ "chunk_text": "Chunk 1: Human: that's nuts to me. I wonder if he was nominated?\nChunk 2: Assistant: i dont think so but im not for sure on that. the oscars are the oldest worldwide entertainment award show\nChunk 3: Human: Did you ever see black panther? I feel like that should have been nominated.", "dialogue_t...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: that's nuts to me. I wonder if he was nominated?", "role": "user", "streaming_reasoning": "The user mentions Human: that's nuts to me. I wonder if he was nominate...
{ "answer": "i actually couldnt get into it. i feel like it was nominated for something. did you know black panther is richer than tony stark?!", "reasoning": "Across the dialogue, the user discusses \"that's nuts to me. I wonder if he was.\" over 3 turns. The answer should respond to the latest user turn naturally...
{ "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_17f8ebfa-7c48-4762-8c89-9343544b6a92", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001270
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for some information.", "turn_id": 2 }, { "role": "user", "text": "um i'm looking for a particular attraction.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for some information.\nChunk 3: um i'm looking for a particular attraction.", "dialogue_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for some information.\nChunk 3: um i'm looking for a particular attraction.", "instruction": "Help the user complet...
{ "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 attraction. Could you share the area, type?", "reasoning": "Across the dialogue, the user is searching for information. Key context: yes, i'm looking for some information; um i'm looking for a particular attraction. The answer should focus on the latest user turn while incorporating...
{ "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": "SNG0087", "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_000379
train
audio
multi_turn
[ { "role": "user", "text": "Human: haha I want to eat that! its crazy that he's 40 and still in that good shape, must be the avocado!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Maybe they say it is super healthy. I guess his book is being dubbed as the Athlete's Bible.", ...
{ "chunk_text": "Chunk 1: Human: haha I want to eat that! its crazy that he's 40 and still in that good shape, must be the avocado!\nChunk 2: Assistant: Maybe they say it is super healthy. I guess his book is being dubbed as the Athlete's Bible.\nChunk 3: Human: yup you're right, do you watch a lot of football games ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: haha I want to eat that! its crazy that he's 40 and still in that good shape, must be the avocado!", "role": "user", "streaming_reasoning": "The user mentions ask...
{ "answer": "I do from time to time but I am not fully dedicated. How about you?", "reasoning": "Across the dialogue, the user is wanting to book is being dubbed as the athlete's bible. Key context: Human: haha I want to eat that; its crazy that he's 40 and still in that good shape, must be the avocado; Assistant: ...
{ "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_6a3dddc7-01d3-4d4a-ad54-0929454768ab", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001271
train
audio
multi_turn
[ { "role": "user", "text": "okay. um, can i just find out about the latest strain.", "turn_id": 1 }, { "role": "assistant", "text": "okay. uh, can i put that for two people, please.", "turn_id": 2 }, { "role": "user", "text": "it is 0 6, 8 3.", "turn_id": 3 }, { "r...
{ "chunk_text": "Chunk 1: okay. um, can i just find out about the latest strain.\nChunk 2: okay. uh, can i put that for two people, please.\nChunk 3: it is 0 6, 8 3.\nChunk 4: 0 8 2 0.\nChunk 5: 8 1 9 4.\nChunk 6: 8, 5 6 4.\nChunk 7: yup.\nChunk 8: no, that's all. thank you.", "dialogue_text": "Chunk 1: okay. um, c...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. um, can i just find out about the latest strain.", "role": "user", "streaming_reasoning": "The user mentions Okay. um, can i just find out about the latest strain....
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for um, can i just find out about the latest strain. Key context: um, can i just find out about the latest strain; uh, can i put that for two people, please; it is 0 6,...
{ "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": "MUL3257", "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_001272
train
audio
multi_turn
[ { "role": "user", "text": "i am looking for a place to dine in the center of cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "um so the restaurant should be an expensive price range.", "turn_id": 2 }, { "role": "user", "text": "i prefer the chinese. are you talkin...
{ "chunk_text": "Chunk 1: i am looking for a place to dine in the center of cambridge.\nChunk 2: um so the restaurant should be an expensive price range.\nChunk 3: i prefer the chinese. are you talking.\nChunk 4: so can you help me to book a table for five people in the evening on friday.\nChunk 5: before 6 pm, pleas...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i am looking for a place to dine in the center of cambridge.", "role": "user", "streaming_reasoning": "The user mentions I am looking for a place to dine in the center o...
{ "answer": "I can help book that. Could you provide the food?", "reasoning": "Across the dialogue, the user is searching for place to dine in the center of cambridge. Key context: i am looking for a place to dine in the center of cambridge; um so the restaurant should be an expensive price range; i prefer the chin...
{ "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": "MUL0576", "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_001273
train
audio
multi_turn
[ { "role": "user", "text": "okay.", "turn_id": 1 }, { "role": "assistant", "text": "you.", "turn_id": 2 }, { "role": "user", "text": "okay, i think i will book that one.", "turn_id": 3 }, { "role": "assistant", "text": "yu. it's 4 people 5 miles. on wednesday."...
{ "chunk_text": "Chunk 1: okay.\nChunk 2: you.\nChunk 3: okay, i think i will book that one.\nChunk 4: yu. it's 4 people 5 miles. on wednesday.\nChunk 5: is um also want to book a taxi. to commit between two places.\nChunk 6: hello.\nChunk 7: i don't much. yes.\nChunk 8: i would just make sure that i don't have to wa...
{ "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 departure, destination, time?", "reasoning": "Across the dialogue, the user is wanting to book that one. Key context: okay, i think i will book that one; it's 4 people 5 miles; on wednesday; is um also want to book a taxi. The answer should focus on the lates...
{ "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": "MUL3513", "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_000380
train
audio
multi_turn
[ { "role": "user", "text": "Human: No I did not know that! Furthermore, Rip curl is a company that manufactures in North Korea but labels it as made in China.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Hahah go figure. DO you know how fashion aficionados can tell if you need...
{ "chunk_text": "Chunk 1: Human: No I did not know that! Furthermore, Rip curl is a company that manufactures in North Korea but labels it as made in China.\nChunk 2: Assistant: Hahah go figure. DO you know how fashion aficionados can tell if you need your clothes tailored?\nChunk 3: Human: Interesting. Speaking of f...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: No I did not know that! Furthermore, Rip curl is a company that manufactures in North Korea but labels it as made in China.", "role": "user", "streaming_reasoning...
{ "answer": "That is strange to me but I guess it worked for them. Do you know how the tipping of the hat originated/.", "reasoning": "Across the dialogue, the user is asking for help with your clothes tailored. Key context: Human: No I did not know that; Furthermore, Rip curl is a company that manufactures in Nort...
{ "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_adcef6d7-f2b3-44f6-b019-82c918c69060", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000381
train
audio
multi_turn
[ { "role": "user", "text": "Human: Hi! Are you a football fan?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Hi! Yes I am a football fan. I prefer the American football than 'football' as some like to call in other countries when referring to soccer, do you?", "turn_id": 2 ...
{ "chunk_text": "Chunk 1: Human: Hi! Are you a football fan?\nChunk 2: Assistant: Hi! Yes I am a football fan. I prefer the American football than 'football' as some like to call in other countries when referring to soccer, do you?\nChunk 3: Human: I would say I am more of a soccer fan, but I follow some football. Ha...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Hi! Are you a football fan?", "role": "user", "streaming_reasoning": "The user mentions Human: Hi! Are you a football fan?. It is not yet clear whether the user n...
{ "answer": "I only know that it is something to do with Tom Brady and that's what the \"TB\" stands for, but what does the 12 stand for?", "reasoning": "Across the dialogue, the user discusses \"Hi! Are you a football fan?\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the...
{ "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_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_multidialog_v02_000382
train
audio
multi_turn
[ { "role": "user", "text": "Human: A good amount of information, it's a very interesting topic. You have nay questions?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: What was the first cloned pet?", "turn_id": 2 }, { "role": "user", "text": "Human: I think it wa...
{ "chunk_text": "Chunk 1: Human: A good amount of information, it's a very interesting topic. You have nay questions?\nChunk 2: Assistant: What was the first cloned pet?\nChunk 3: Human: I think it was a cat named \"Copy Cat\". You can even get your dog cloned for 150K in Korea.", "dialogue_text": "Chunk 1: Human: ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: A good amount of information, it's a very interesting topic. You have nay questions?", "role": "user", "streaming_reasoning": "The user mentions asking for recomm...
{ "answer": "Cool name. I'm not sure I'd want a clone of my dog.", "reasoning": "Across the dialogue, the user discusses \"A good amount of information, it's a very interesting.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoni...
{ "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_5054d997-fa74-4a98-89d1-11a05cd9b6f1", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_001274
train
audio
multi_turn
[ { "role": "user", "text": "hi, i need to put a taxi.", "turn_id": 1 }, { "role": "assistant", "text": "i'm departing from a dairy cookhouse and one shop.", "turn_id": 2 }, { "role": "user", "text": "uh, i'm going to the sita tenderly.", "turn_id": 3 }, { "role": "...
{ "chunk_text": "Chunk 1: hi, i need to put a taxi.\nChunk 2: i'm departing from a dairy cookhouse and one shop.\nChunk 3: uh, i'm going to the sita tenderly.\nChunk 4: uh, i. i'm looking for a taxi at least after 6 15 p m.\nChunk 5: and my phone number is 6 5 1.\nChunk 6: 6, 4, 7.", "dialogue_text": "Chunk 1: hi, ...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, i need to put a taxi.", "role": "user", "streaming_reasoning": "The user mentions Hi, i need to put a taxi. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help find a matching taxi option with those details.", "reasoning": "Across the dialogue, the user is searching for taxi at least after 6 15 p m. Key context: hi, i need to put a taxi; i'm departing from a dairy cookhouse and one shop; uh, i'm going to the sita tenderly; i'm looking for a taxi at...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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": "SNG0105", "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_001275
train
audio
multi_turn
[ { "role": "user", "text": "yes, that is correct.", "turn_id": 1 }, { "role": "assistant", "text": "it before me. my husband, our invent and four children.", "turn_id": 2 }, { "role": "user", "text": "yes, that is correct.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: yes, that is correct.\nChunk 2: it before me. my husband, our invent and four children.\nChunk 3: yes, that is correct.\nChunk 4: no, except where necessary.\nChunk 5: thank you. do i need to pay for instant belt as well.\nChunk 6: oh, that wonderful too.\nChunk 7: and could you just confirm...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, that is correct.", "role": "user", "streaming_reasoning": "The user mentions Yes, that is correct. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "Sure. I can provide the leaveat for the matching train option.", "reasoning": "Across the dialogue, the user is talking about to pay for instant belt as well. Key context: yes, that is correct; it before me; my husband, our invent and four children; yes, that is correct. 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": "SNG0051", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }