id
large_stringlengths
23
28
split
large_stringclasses
1 value
modality
large_stringclasses
1 value
turn_type
large_stringclasses
1 value
dialogue
listlengths
1
8
input
dict
streaming
dict
target
dict
taxonomy
dict
quality
dict
source
dict
metadata
dict
audio_spokenwoz_v02_002422
train
audio
multi_turn
[ { "role": "user", "text": "7 2 5 9.", "turn_id": 1 }, { "role": "assistant", "text": "4, 7, 3, 7.", "turn_id": 2 }, { "role": "user", "text": "alright great i'm also looking for a place to stay it should be located in the north and of the guesthouse and it should also", "...
{ "chunk_text": "Chunk 1: 7 2 5 9.\nChunk 2: 4, 7, 3, 7.\nChunk 3: alright great i'm also looking for a place to stay it should be located in the north and of the guesthouse and it should also\nChunk 4: be in the moderate price range\nChunk 5: could you recommend one to me? i would need the address phone number and, ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "7 2 5 9.", "role": "user", "streaming_reasoning": "The user mentions 7 2 5 9. 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 phone, address, internet for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for place to stay it should be located in the north. Key context: alright great i'm also looking for a place to stay it should be located in the north and of the gu...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3151", "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_002423
train
audio
multi_turn
[ { "role": "user", "text": "hi, hello.", "turn_id": 1 }, { "role": "assistant", "text": "um yes, i'm looking for a restaurant which serves lebanese food. do you have any recommendation.", "turn_id": 2 }, { "role": "user", "text": "yeah, price won't be a problem. maybe expensiv...
{ "chunk_text": "Chunk 1: hi, hello.\nChunk 2: um yes, i'm looking for a restaurant which serves lebanese food. do you have any recommendation.\nChunk 3: yeah, price won't be a problem. maybe expensive would be good and then i would like to go to the north of the city.\nChunk 4: um how about asian oriental food.\nChu...
{ "num_checkpoints": 6, "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 book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for restaurant which serves lebanese food. Key context: um yes, i'm looking for a restaurant which serves lebanese food; do you have any recommendatio...
{ "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": "MUL0331", "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_002424
train
audio
multi_turn
[ { "role": "user", "text": "0 6, 8.", "turn_id": 1 }, { "role": "assistant", "text": "4, 1, 3.", "turn_id": 2 }, { "role": "user", "text": "4 1, 7.", "turn_id": 3 }, { "role": "assistant", "text": "yeah.", "turn_id": 4 }, { "role": "user", "text...
{ "chunk_text": "Chunk 1: 0 6, 8.\nChunk 2: 4, 1, 3.\nChunk 3: 4 1, 7.\nChunk 4: yeah.\nChunk 5: i know that will be fine thank you so much i am however looking for a recommendation for a restaurant at the center of the\nChunk 6: town in a moderate prices\nChunk 7: ok, thank you.\nChunk 8: okay, i'd like to book a ta...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "0 6, 8.", "role": "user", "streaming_reasoning": "The user mentions 0 6, 8. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "I can help book that. Could you provide the food?", "reasoning": "Across the dialogue, the user is searching for table case for the same group of seven people at 9 o'clock on the same day. Key context: i know that will be fine thank you so much i am however looking for a recommendation for a restaurant...
{ "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": "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_spokenwoz_v02_002425
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is erik. i need to find the phone number.", "turn_id": 1 }, { "role": "assistant", "text": "i need to contact information for a special department in the hospital.", "turn_id": 2 }, { "role": "user", "text": "i am looking for an internet...
{ "chunk_text": "Chunk 1: hi, my name is erik. i need to find the phone number.\nChunk 2: i need to contact information for a special department in the hospital.\nChunk 3: i am looking for an internet department.", "dialogue_text": "Chunk 1: hi, my name is erik. i need to find the phone number.\nChunk 2: i need to ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is erik. i need to find the phone number.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is erik. i need to find the phone number. I...
{ "answer": "I can help find a matching hospital option with those details.", "reasoning": "Across the dialogue, the user is searching for internet department. Key context: hi, my name is erik; i need to find the phone number; i need to contact information for a special department in the hospital; i am looking for ...
{ "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": "SNG0575", "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_000687
train
audio
multi_turn
[ { "role": "user", "text": "Human: Should have known it would have Arabian in it. Those are beautiful horses! Lipizzaners are too! Did you know that they are actually born black or brown and it takes up to 6 years before they tu", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I h...
{ "chunk_text": "Chunk 1: Human: Should have known it would have Arabian in it. Those are beautiful horses! Lipizzaners are too! Did you know that they are actually born black or brown and it takes up to 6 years before they turn white?\nChunk 2: Assistant: I had no idea! Did you know horses are ticklish! What a thing...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Should have known it would have Arabian in it. Those are beautiful horses! Lipizzaners are too! Did you know that they are actually born black or brown and it takes up to 6 y...
{ "answer": "True! the us hockey team lost to a england high school team!", "reasoning": "Across the dialogue, the user is asking for help with human: should have known it would have arabian in it. Key context: Human: Should have known it would have Arabian in it; Those are beautiful horses; Lipizzaners are too; Di...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_a44c497a-03a8-44e4-95f1-6442e1a5d09d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002426
train
audio
multi_turn
[ { "role": "user", "text": "good afternoon.", "turn_id": 1 }, { "role": "assistant", "text": "yes. uh, could you please assist me in looking for a particular restaurant, please.", "turn_id": 2 }, { "role": "user", "text": "yes. um, it's called the varsity restaurant, i believe...
{ "chunk_text": "Chunk 1: good afternoon.\nChunk 2: yes. uh, could you please assist me in looking for a particular restaurant, please.\nChunk 3: yes. um, it's called the varsity restaurant, i believe.\nChunk 4: um, could you please. uh, book a table for 7 people, please.\nChunk 5: um could you please make it for thu...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "good afternoon.", "role": "user", "streaming_reasoning": "The user mentions Good afternoon. It is not yet clear whether the user needs the full scope of the user's reque...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is searching for particular restaurant. Key context: good afternoon; uh, could you please assist me in looking for a particular restaurant, please; um, it's called the varsity restaurant, i beli...
{ "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": "MUL2464", "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_000688
train
audio
multi_turn
[ { "role": "user", "text": "Human: Nice. The actor is Deep Roy", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Never heard of \"Deep Roy\" until now. Wow, the world's longest piece of fiction is 4 million words long. Take that Tolstoy!", "turn_id": 2 }, { "role": "use...
{ "chunk_text": "Chunk 1: Human: Nice. The actor is Deep Roy\nChunk 2: Assistant: Never heard of \"Deep Roy\" until now. Wow, the world's longest piece of fiction is 4 million words long. Take that Tolstoy!\nChunk 3: Human: Niceee. Do you watch horror movies?", "dialogue_text": "Chunk 1: Human: Nice. The actor is D...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Nice. The actor is Deep Roy", "role": "user", "streaming_reasoning": "The user mentions Human: Nice. The actor is Deep Roy. It is not yet clear whether the user n...
{ "answer": "I watch very few. I can't stand slasher movies but I like stuff like Alien. Hard to believe E.T.", "reasoning": "Across the dialogue, the user discusses \"Nice. The actor is Deep Roy\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "r...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_b1d6df00-a516-4542-a516-8247320d3045", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002427
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i am hoping that you will be able to help me so i am going to be traveling to cambridge and i am really looking", "turn_id": 2 }, { "role": "user", "text": "forward to trying some of the local...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i am hoping that you will be able to help me so i am going to be traveling to cambridge and i am really looking\nChunk 3: forward to trying some of the local restaurants and places like that\nChunk 4: okay. so 1st of all, i'm looking for a twig restaurant. um in the expensiv...
{ "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 with the restaurant. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for twig restaurant. Key context: i am hoping that you will be able to help me so i am going to be traveling to cambridge and i am really looking forward to trying some of the local rest...
{ "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": "MUL3554", "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_002428
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is abraham couch on trying.", "turn_id": 1 }, { "role": "assistant", "text": "uh, in my nose i'm looking for information in companies about train services.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hi, my name is abraham couch on trying.\nChunk 2: uh, in my nose i'm looking for information in companies about train services.", "dialogue_text": "Chunk 1: hi, my name is abraham couch on trying.\nChunk 2: uh, in my nose i'm looking for information in companies about train services.", "...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is abraham couch on trying.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is abraham couch on trying. It is not yet clear whether t...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for information in companies about train services. Key context: hi, my name is abraham couch on trying; uh, in my nose i'm looking for information in companies about tr...
{ "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": "MUL1792", "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_000689
train
audio
multi_turn
[ { "role": "user", "text": "Human: Good morning! Are you a football fan?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I am a football fan, what about you?", "turn_id": 2 }, { "role": "user", "text": "Human: I'm a fan! Did you know that ESPN won an Emmy for crea...
{ "chunk_text": "Chunk 1: Human: Good morning! Are you a football fan?\nChunk 2: Assistant: I am a football fan, what about you?\nChunk 3: Human: I'm a fan! Did you know that ESPN won an Emmy for creating the yellow superimposed first down line on tv?", "dialogue_text": "Chunk 1: Human: Good morning! Are you a foot...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Good morning! Are you a football fan?", "role": "user", "streaming_reasoning": "The user mentions Human: Good morning! Are you a football fan?. It is not yet clea...
{ "answer": "Yeah, I heard it seems like that is pretty cool.", "reasoning": "Across the dialogue, the user discusses \"Good morning! Are you a football.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue,...
{ "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_e8c39f50-c50b-4f1b-a5a1-802f163272a3", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000690
train
audio
multi_turn
[ { "role": "user", "text": "Human: I watch mostly college, but I tend to watch most during playoff time.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That's cool, I like NFL football.", "turn_id": 2 }, { "role": "user", "text": "Human: Did you catch the superbo...
{ "chunk_text": "Chunk 1: Human: I watch mostly college, but I tend to watch most during playoff time.\nChunk 2: Assistant: That's cool, I like NFL football.\nChunk 3: Human: Did you catch the superbowl this year? Pretty soon Brady is going to run out of fingers to put those rings on!", "dialogue_text": "Chunk 1: H...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I watch mostly college, but I tend to watch most during playoff time.", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not y...
{ "answer": "Actually, I did. That thing was too long, though. I sat for 3 hours, makes me mad to think that the average NFL game has only 11 minutes of actual live gameplay.", "reasoning": "Across the dialogue, the user discusses \"I watch mostly college, but I tend to watch most during.\" over 3 turns. The answer...
{ "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_17100bb3-85f1-4601-9c68-56299110fd05", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002429
train
audio
multi_turn
[ { "role": "user", "text": "s. i. number is 1 3 2 5. 3 1 0, 5, 7.", "turn_id": 1 }, { "role": "assistant", "text": "3 6 4 9 7 3 1.", "turn_id": 2 }, { "role": "user", "text": "all right, that is fantastic. thank you.", "turn_id": 3 }, { "role": "assistant", "te...
{ "chunk_text": "Chunk 1: s. i. number is 1 3 2 5. 3 1 0, 5, 7.\nChunk 2: 3 6 4 9 7 3 1.\nChunk 3: all right, that is fantastic. thank you.\nChunk 4: yeah. um, i would like to get, um, uh. oh, sorry, i'm also looking for places go to in town.\nChunk 5: um is the lovely place to be in the center of the town, please.\n...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "s. i. number is 1 3 2 5. 3 1 0, 5, 7.", "role": "user", "streaming_reasoning": "The user mentions S. i. number is 1 3 2 5. 3 1 0, 5, 7. It is not yet clear whether the u...
{ "answer": "Sure. I can provide the address for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for places go to in town. Key context: number is 1 3 2 5; 3 1 0, 5, 7; 3 6 4 9 7 3 1; all right, that is fantastic. The answer should focus on the latest user turn while incorp...
{ "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": "MUL0620", "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_002430
train
audio
multi_turn
[ { "role": "user", "text": "no, uh, please tell me it's a test.", "turn_id": 1 }, { "role": "assistant", "text": "okay, got it and i want to know it's post code.", "turn_id": 2 }, { "role": "user", "text": "no, that's all.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: no, uh, please tell me it's a test.\nChunk 2: okay, got it and i want to know it's post code.\nChunk 3: no, that's all.\nChunk 4: hello is that customer service center.\nChunk 5: well i'm having my trip on a in cambridge now and i want to look for a train to live there could you please help"...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "no, uh, please tell me it's a test.", "role": "user", "streaming_reasoning": "The user mentions No, uh, please tell me it's a test. It is not yet clear whether the user ...
{ "answer": "I can help with the train. Could you share the destination, day, time?", "reasoning": "Across the dialogue, the user discusses \"no, uh, please tell me it's a.\" over 5 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: A...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0334", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002431
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "ya um so i'm looking for a place to stay uh it should include free parking and it should be a two star uh hotel", "turn_id": 2 }, { "role": "user", "text": "in the north", "turn_id"...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: ya um so i'm looking for a place to stay uh it should include free parking and it should be a two star uh hotel\nChunk 3: in the north", "dialogue_text": "Chunk 1: hello. hello.\nChunk 2: ya um so i'm looking for a place to stay uh it should include free parking and...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "I can help with the hotel. Could you share the price?", "reasoning": "Across the dialogue, the user is searching for place to stay uh it should include free parking. Key context: ya um so i'm looking for a place to stay uh it should include free parking and it should be a two star uh hotel in the north...
{ "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": "MUL3225", "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_002432
train
audio
multi_turn
[ { "role": "user", "text": "if.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i would also put the train. on the same day.", "turn_id": 2 }, { "role": "user", "text": "yeah.", "turn_id": 3 }, { "role": "assistant", "text": "the train. may be a gorgeous...
{ "chunk_text": "Chunk 1: if.\nChunk 2: yes, i would also put the train. on the same day.\nChunk 3: yeah.\nChunk 4: the train. may be a gorgeous app.\nChunk 5: yes.\nChunk 6: kings like.\nChunk 7: a cambridge.\nChunk 8: beef.", "dialogue_text": "Chunk 1: if.\nChunk 2: yes, i would also put the train. on the same da...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "if.", "role": "user", "streaming_reasoning": "The user mentions If. It is not yet clear whether the user needs the full scope of the user's request. The assistant should...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is talking about yes, i would also put the train. Key context: yes, i would also put the train; on the same day; may be a gorgeous app; a cambridge. The answer should focus on the latest user turn ...
{ "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": "SpokenWOZ", "dialogue_id": "MUL2888", "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_002433
train
audio
multi_turn
[ { "role": "user", "text": "yes, and she'll depart from where i'm traveling to.", "turn_id": 1 }, { "role": "assistant", "text": "yes, thank you very much. do you if you find a problem. please tell me some information.", "turn_id": 2 }, { "role": "user", "text": "sure, that's ...
{ "chunk_text": "Chunk 1: yes, and she'll depart from where i'm traveling to.\nChunk 2: yes, thank you very much. do you if you find a problem. please tell me some information.\nChunk 3: sure, that's quite acceptable for me.\nChunk 4: well, i want to know the departure time of the train.\nChunk 5: got it manual the p...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, and she'll depart from where i'm traveling to.", "role": "user", "streaming_reasoning": "The user mentions Yes, and she'll depart from where i'm traveling to. It is...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: yes, and she'll depart from where i'm traveling to; yes, thank you very much; do you if you find a problem; please tell me some information....
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1141", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002434
train
audio
multi_turn
[ { "role": "user", "text": "i'm looking for a particular restaurant. it's called papa restaurant.", "turn_id": 1 }, { "role": "assistant", "text": "yes. can you tell me the food type that they serve.", "turn_id": 2 }, { "role": "user", "text": "okay. and can i get the phone nu...
{ "chunk_text": "Chunk 1: i'm looking for a particular restaurant. it's called papa restaurant.\nChunk 2: yes. can you tell me the food type that they serve.\nChunk 3: okay. and can i get the phone number, please.\nChunk 4: okay, perfect. thank you so much for that.\nChunk 5: no, that'll be all.\nChunk 6: yes, you ca...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm looking for a particular restaurant. it's called papa restaurant.", "role": "user", "streaming_reasoning": "The user mentions searching for papa. It is not yet clear...
{ "answer": "Sure. I can provide the food, phone for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for particular restaurant. Key context: i'm looking for a particular restaurant; it's called papa restaurant; can you tell me the food type that they serve; and can i get t...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG1077", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000691
train
audio
multi_turn
[ { "role": "user", "text": "Human: I was born in Europe (Poland ) - we are born with soccer balls glued to our feet:)", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I am well aware of the passion for soccer that most of the World has. And my God Bless Poland, one of the few sane...
{ "chunk_text": "Chunk 1: Human: I was born in Europe (Poland ) - we are born with soccer balls glued to our feet:)\nChunk 2: Assistant: I am well aware of the passion for soccer that most of the World has. And my God Bless Poland, one of the few sane countries left in Europe. Go Poland\nChunk 3: Human: Now that's in...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I was born in Europe (Poland ) - we are born with soccer balls glued to our feet:)", "role": "user", "streaming_reasoning": "The user mentions talking about Human...
{ "answer": "Poland currently has a strong economy and strong leadership and has a true identity as a country. Most of the other countries in Europe, especially W. Europe have lost that.", "reasoning": "Across the dialogue, the user is asking for help with human: i was born in europe (poland ) - we are born with so...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "explain_cause" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_d3b7776e-706c-48c0-9f8d-3ed04fe79c09", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002435
train
audio
multi_turn
[ { "role": "user", "text": "three, oh i guess yeah three zero two.", "turn_id": 1 }, { "role": "assistant", "text": "four, nine, nine.", "turn_id": 2 }, { "role": "user", "text": "five four zero.", "turn_id": 3 }, { "role": "assistant", "text": "one name.", ...
{ "chunk_text": "Chunk 1: three, oh i guess yeah three zero two.\nChunk 2: four, nine, nine.\nChunk 3: five four zero.\nChunk 4: one name.\nChunk 5: do you also have some information on restaurants in the area.\nChunk 6: great. i'm also looking for a cheap restaurant that serves international food um somewhere in the...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "three, oh i guess yeah three zero two.", "role": "user", "streaming_reasoning": "The user mentions Three, oh i guess yeah three zero two. It is not yet clear whether the...
{ "answer": "Sure. I can provide the phone for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for cheap restaurant that serves international food um somewhere in the north. Key context: three, oh i guess yeah three zero two; four, nine, nine; five four zero; do you also h...
{ "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": "MUL2324", "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_000692
train
audio
multi_turn
[ { "role": "user", "text": "Human: for sure lol! Did you know police have their own youtube for their job called blutube.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I heard that. I guess they post training videos there. Pretty cool.", "turn_id": 2 }, { "role": "u...
{ "chunk_text": "Chunk 1: Human: for sure lol! Did you know police have their own youtube for their job called blutube.\nChunk 2: Assistant: I heard that. I guess they post training videos there. Pretty cool.\nChunk 3: Human: that is cool. Do you watch bird videos on youtube at all. I like birds", "dialogue_text": ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: for sure lol! Did you know police have their own youtube for their job called blutube.", "role": "user", "streaming_reasoning": "The user mentions talking about H...
{ "answer": "My favorite bird is the dodo bird!", "reasoning": "Across the dialogue, the user discusses \"for sure lol! Did you know police have their own youtube.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_5724f961-ce3a-4899-ae4f-e900809c69a0", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002436
train
audio
multi_turn
[ { "role": "user", "text": "hello, good day.", "turn_id": 1 }, { "role": "assistant", "text": "uh, i'm i'm planning my trip in cambridge and i'm looking for a short end.", "turn_id": 2 }, { "role": "user", "text": "the restaurant should serve spanish food and should be in the ...
{ "chunk_text": "Chunk 1: hello, good day.\nChunk 2: uh, i'm i'm planning my trip in cambridge and i'm looking for a short end.\nChunk 3: the restaurant should serve spanish food and should be in the middle of.\nChunk 4: yes, ma'am.\nChunk 5: and the restaurant should be in the boundary price range, please.", "dial...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, good day.", "role": "user", "streaming_reasoning": "The user mentions Hello, good day. It is not yet clear whether the user needs the full scope of the user's req...
{ "answer": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for short end. Key context: hello, good day; uh, i'm i'm planning my trip in cambridge and i'm looking for a short end; the restaurant should serve spanish food and should be in t...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0972", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000693
train
audio
multi_turn
[ { "role": "user", "text": "Human: I imagine this number in the millions taking into account he had a 54 year broadcasting carreer, so sad, but he was old.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I like that he used this phrase alot Whoa, Nellie!", "turn_id": 2 }, ...
{ "chunk_text": "Chunk 1: Human: I imagine this number in the millions taking into account he had a 54 year broadcasting carreer, so sad, but he was old.\nChunk 2: Assistant: I like that he used this phrase alot Whoa, Nellie!\nChunk 3: Human: That was a good phrase I liked it as well, did you see the beer comercial, ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I imagine this number in the millions taking into account he had a 54 year broadcasting carreer, so sad, but he was old.", "role": "user", "streaming_reasoning": ...
{ "answer": "I didn't. I did see the ABC would not let him retire at 70!", "reasoning": "Across the dialogue, the user discusses \"I imagine this number in the millions taking into account.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "respons...
{ "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_04eea955-7ad7-4c3c-aa0b-0fc16e89ae1d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002437
train
audio
multi_turn
[ { "role": "user", "text": "hello, can we.", "turn_id": 1 }, { "role": "assistant", "text": "easy to customer service.", "turn_id": 2 }, { "role": "user", "text": "i am traveling in the king's lane.", "turn_id": 3 }, { "role": "assistant", "text": "i am looking...
{ "chunk_text": "Chunk 1: hello, can we.\nChunk 2: easy to customer service.\nChunk 3: i am traveling in the king's lane.\nChunk 4: i am looking for a train.\nChunk 5: i want to go to cambridge.\nChunk 6: yes, you're right.", "dialogue_text": "Chunk 1: hello, can we.\nChunk 2: easy to customer service.\nChunk 3: i ...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, can we.", "role": "user", "streaming_reasoning": "The user mentions Hello, can we. 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 day, time?", "reasoning": "Across the dialogue, the user is searching for train. Key context: hello, can we; easy to customer service; i am traveling in the king's lane; i am looking for a train. The answer should focus on the latest user turn while incorp...
{ "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": "SNG0010", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002438
train
audio
multi_turn
[ { "role": "user", "text": "you are most welcome.", "turn_id": 1 }, { "role": "assistant", "text": "please book it for myself on saturday at 1115.", "turn_id": 2 }, { "role": "user", "text": "that's no problem. how about 1015.", "turn_id": 3 }, { "role": "assistant...
{ "chunk_text": "Chunk 1: you are most welcome.\nChunk 2: please book it for myself on saturday at 1115.\nChunk 3: that's no problem. how about 1015.\nChunk 4: which info do you need.\nChunk 5: this will be on saturday at. 1015 then.\nChunk 6: my name is spelt ca ha r. le f, charles.\nChunk 7: it is about y ou ng you...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "you are most welcome.", "role": "user", "streaming_reasoning": "The user mentions You are most welcome. 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, food, price?", "reasoning": "Across the dialogue, the user is wanting to book it for myself on saturday at 1115. Key context: you are most welcome; please book it for myself on saturday at 1115; that's no problem; how about 1015. The answer should focus...
{ "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": "MUL3796", "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_002439
train
audio
multi_turn
[ { "role": "user", "text": "um can you please search in the north.", "turn_id": 1 }, { "role": "assistant", "text": "okay. and can you please search for a guesthouse type of place.", "turn_id": 2 }, { "role": "user", "text": "okay, correct. yes. can you please check if they've...
{ "chunk_text": "Chunk 1: um can you please search in the north.\nChunk 2: okay. and can you please search for a guesthouse type of place.\nChunk 3: okay, correct. yes. can you please check if they've got free connectivity.\nChunk 4: okay, thank you.\nChunk 5: okay. and um, can you please check if they have, um, free...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um can you please search in the north.", "role": "user", "streaming_reasoning": "The user mentions Um can you please search in the north. It is not yet clear whether the...
{ "answer": "Sure. I can provide the internet, parking for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for guesthouse type of place. Key context: um can you please search in the north; and can you please search for a guesthouse type of place; okay, correct; can you please c...
{ "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": "MUL0750", "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_002440
train
audio
multi_turn
[ { "role": "user", "text": "got it.", "turn_id": 1 }, { "role": "assistant", "text": "mm. i think that's okay.", "turn_id": 2 }, { "role": "user", "text": "sure, please make a reservation for us.", "turn_id": 3 }, { "role": "assistant", "text": "mm. mm, they ar...
{ "chunk_text": "Chunk 1: got it.\nChunk 2: mm. i think that's okay.\nChunk 3: sure, please make a reservation for us.\nChunk 4: mm. mm, they are my friends and me. um, i have 7 friends.\nChunk 5: right, totally for 8 people.\nChunk 6: yes, mining numbers should be. 7 5 2 8.\nChunk 7: 3, 6 double 5.\nChunk 8: 8 7 9 3...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "got it.", "role": "user", "streaming_reasoning": "The user mentions Got it. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "I can help book that. Could you provide the departure, destination, day?", "reasoning": "Across the dialogue, the user is wanting to book i think that's okay. Key context: i think that's okay; sure, please make a reservation for us; mm, they are my friends and me; um, i have 7 friends. The answer shoul...
{ "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": "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_spokenwoz_v02_002441
train
audio
multi_turn
[ { "role": "user", "text": "0 0, 3.", "turn_id": 1 }, { "role": "assistant", "text": "and follows 8 3, 3.", "turn_id": 2 }, { "role": "user", "text": "hello.", "turn_id": 3 }, { "role": "assistant", "text": "uh, yes, please. and. i don't want to be in the west....
{ "chunk_text": "Chunk 1: 0 0, 3.\nChunk 2: and follows 8 3, 3.\nChunk 3: hello.\nChunk 4: uh, yes, please. and. i don't want to be in the west. so. what about any ah directions facing the list maybe.\nChunk 5: um yes, it sounds great.\nChunk 6: okay, then when do they open? i want know their open hours.\nChunk 7: um...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "0 0, 3.", "role": "user", "streaming_reasoning": "The user mentions 0 0, 3. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "I can help with the restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is searching for particular restaurant named. Key context: and follows 8 3, 3; uh, yes, please; i don't want to be in the west; what about any ah directions facing the list maybe. The an...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "SpokenWOZ", "dialogue_id": "MUL0467", "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_002442
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes. um, i'm hoping that you're going to be able to help me so i don't like to be treasure.", "turn_id": 2 }, { "role": "user", "text": "are you able to see what the operating hours there.", ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes. um, i'm hoping that you're going to be able to help me so i don't like to be treasure.\nChunk 3: are you able to see what the operating hours there.\nChunk 4: fantastic. and the post code, please.\nChunk 5: wonderful. can i ask that this is a book talking spot me there....
{ "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": "Sure. I can help with the postcode; first I need to identify the right attraction option.", "reasoning": "Across the dialogue, the user is wanting to book talking spot me there. Key context: um, i'm hoping that you're going to be able to help me so i don't like to be treasure; are you able to see what ...
{ "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": "SNG1248", "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_002443
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a train. go to london liverpool street.", "turn_id": 2 }, { "role": "user", "text": "and i want to leave on sunday. maybe leave after a quarter after. 21.", "turn_id":...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a train. go to london liverpool street.\nChunk 3: and i want to leave on sunday. maybe leave after a quarter after. 21.\nChunk 4: yes, and depart from cambridge.\nChunk 5: okay, thank you. if you have the right train for me, then i would love to make a b...
{ "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": "Sure. I can provide the id for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train. Key context: yes, i'm looking for a train; go to london liverpool street; and i want to leave on sunday; maybe leave after a quarter after. The answer should focus on the late...
{ "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": "MUL0452", "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_002444
train
audio
multi_turn
[ { "role": "user", "text": "how. many of the address.", "turn_id": 1 }, { "role": "assistant", "text": "okay, thank you.", "turn_id": 2 }, { "role": "user", "text": "yeah, thank you. i did hear you.", "turn_id": 3 }, { "role": "assistant", "text": "uh, yes, ma'...
{ "chunk_text": "Chunk 1: how. many of the address.\nChunk 2: okay, thank you.\nChunk 3: yeah, thank you. i did hear you.\nChunk 4: uh, yes, ma'am. i am also looking for a place to dine.\nChunk 5: uh, i'm looking for any restaurant in the. but that is at the center of the town and do this is within the molecular pric...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "how. many of the address.", "role": "user", "streaming_reasoning": "The user mentions How. many of the address. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help book that. Could you provide the food, day, time?", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: many of the address; okay, thank you; yeah, thank you; i did hear you. The answer should focus on the latest user turn while incorporating relevant con...
{ "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": "MUL2735", "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_002445
train
audio
multi_turn
[ { "role": "user", "text": "uh, i'm looking for a guess how to stay in cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "uh, i'm looking for, um. guesthouse in modern price range and needs to provide free parking and internet.", "turn_id": 2 }, { "role": "user", "te...
{ "chunk_text": "Chunk 1: uh, i'm looking for a guess how to stay in cambridge.\nChunk 2: uh, i'm looking for, um. guesthouse in modern price range and needs to provide free parking and internet.\nChunk 3: yes, you are correct.\nChunk 4: uh, i prefer to be in the north of cambridge.\nChunk 5: mm mm i think that is go...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, i'm looking for a guess how to stay in cambridge.", "role": "user", "streaming_reasoning": "The user mentions Uh, i'm looking for a guess how to stay in cambridge. I...
{ "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 guess how to stay in cambridge. Key context: uh, i'm looking for a guess how to stay in cambridge; uh, i'm looking for, um; guesthouse in modern p...
{ "category": "daily_life", "subcategory": "shopping_decision", "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": "MUL1923", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002446
train
audio
multi_turn
[ { "role": "user", "text": "thank you. i'm also looking for a particular hotel.", "turn_id": 1 }, { "role": "assistant", "text": "hamilton lodge.", "turn_id": 2 }, { "role": "user", "text": "yes, i would like to book it for myself, my husband and my four children.", "turn_...
{ "chunk_text": "Chunk 1: thank you. i'm also looking for a particular hotel.\nChunk 2: hamilton lodge.\nChunk 3: yes, i would like to book it for myself, my husband and my four children.\nChunk 4: it's actually a number additional. my husband and i and my four children.\nChunk 5: i would like it to book it for three...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "thank you. i'm also looking for a particular hotel.", "role": "user", "streaming_reasoning": "The user mentions Thank you. i'm also looking for a particular hotel. It is...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for particular hotel. Key context: i'm also looking for a particular hotel; hamilton lodge; yes, i would like to book it for myself, my husband and my four children; it's actu...
{ "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": "MUL3088", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000094
train
audio
multi_turn
[ { "role": "user", "text": "They were received in the little office by a man named Markham, who was the jailer.", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: They were received in the little office by a man named Markham, who was the jailer.", "dialogue_text": "Chunk 1: They were received in the little office by a man named Markham, who was the jailer.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "They were received in the little office by a man named Markham, who was the jailer.", "role": "user", "streaming_reasoning": "The user mentions talking about They, Markh...
{ "answer": "It's interesting to see how different contexts like a sports center connect with Markham's role.", "reasoning": "Across the dialogue, the user discusses \"They were received in the little office by a man named.\" over 1 turns. The answer should respond to the latest user turn naturally, maintaining the...
{ "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": "6829-68769-0009-gym", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002447
train
audio
multi_turn
[ { "role": "user", "text": "okay. what about three times.", "turn_id": 1 }, { "role": "assistant", "text": "yes, please.", "turn_id": 2 }, { "role": "user", "text": "yeah, of course. so my first name is donald.", "turn_id": 3 }, { "role": "assistant", "text": "...
{ "chunk_text": "Chunk 1: okay. what about three times.\nChunk 2: yes, please.\nChunk 3: yeah, of course. so my first name is donald.\nChunk 4: and my. my surname is schulz, so let me spell that for. is for sugar. seafood cat.\nChunk 5: h hotel. our fulltime.\nChunk 6: i for india. t for tango.\nChunk 7: zeta fuzzy.\...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. what about three times.", "role": "user", "streaming_reasoning": "The user mentions Okay. what about three times. 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 talking about what about three times. Key context: what about three times; yes, please; yeah, of course; so my first name is donald. The answer should focus on the latest user turn while in...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2929", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002448
train
audio
multi_turn
[ { "role": "user", "text": "uh, if. ellen herman.", "turn_id": 1 }, { "role": "assistant", "text": "a l a n n for net.", "turn_id": 2 }, { "role": "user", "text": "h e rr for rolling.", "turn_id": 3 }, { "role": "assistant", "text": "m a n n for net.", "tur...
{ "chunk_text": "Chunk 1: uh, if. ellen herman.\nChunk 2: a l a n n for net.\nChunk 3: h e rr for rolling.\nChunk 4: m a n n for net.\nChunk 5: uh, that's fine. uh, thank you.\nChunk 6: sorry, i don't want to.\nChunk 7: okay, thank you.\nChunk 8: i think no, thank you.", "dialogue_text": "Chunk 1: uh, if. ellen her...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, if. ellen herman.", "role": "user", "streaming_reasoning": "The user mentions Uh, if. ellen herman. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is talking about ellen herman. Key context: ellen herman; a l a n n for net; h e rr for rolling; m a n n for net. The answer should focus on the latest user turn while incorporating relevant context from ear...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3930", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000694
train
audio
multi_turn
[ { "role": "user", "text": "Human: I did not. Do you like birds?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Again I have a passing fancy, we put up bird feeder outside the back window, that is about it.", "turn_id": 2 }, { "role": "user", "text": "Human: Ther...
{ "chunk_text": "Chunk 1: Human: I did not. Do you like birds?\nChunk 2: Assistant: Again I have a passing fancy, we put up bird feeder outside the back window, that is about it.\nChunk 3: Human: There's an extinct Dodo bird that is actually in the same family as the pigeon.", "dialogue_text": "Chunk 1: Human: I di...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I did not. Do you like birds?", "role": "user", "streaming_reasoning": "The user mentions Human: I did not. Do you like birds?. It is not yet clear whether the us...
{ "answer": "The fate of the Dodo always makes my wife cry. They appear to have been so trusting, which is what to their demise.", "reasoning": "Across the dialogue, the user discusses \"I did not. Do you like birds?\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conver...
{ "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_1484ed33-6ce6-49cf-9971-e166cabf05de", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002449
train
audio
multi_turn
[ { "role": "user", "text": "he. yes, it will be perfect.", "turn_id": 1 }, { "role": "assistant", "text": "is.", "turn_id": 2 }, { "role": "user", "text": "okay. like how about one night.", "turn_id": 3 }, { "role": "assistant", "text": "by j for jacob o for or...
{ "chunk_text": "Chunk 1: he. yes, it will be perfect.\nChunk 2: is.\nChunk 3: okay. like how about one night.\nChunk 4: by j for jacob o for orange h vana and vanilla laughing. alpha lima i for india and for.\nChunk 5: d for dinosaurs for sugar. and wifi yellow.\nChunk 6: okay, don't mind is. capitol j. for jacob ca...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "he. yes, it will be perfect.", "role": "user", "streaming_reasoning": "The user mentions He. yes, it will be perfect. It is not yet clear whether the user needs the full...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is talking about yes, it will be perfect. Key context: yes, it will be perfect; like how about one night; by j for jacob o for orange h vana and vanilla laughing; alpha lima i for india...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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": "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_000695
train
audio
multi_turn
[ { "role": "user", "text": "Human: I'm doing good thanks for asking. I think it's different. What about you?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: It is different, I agree. I am not sure how much power they have. It seems like they can do a little more than a president ...
{ "chunk_text": "Chunk 1: Human: I'm doing good thanks for asking. I think it's different. What about you?\nChunk 2: Assistant: It is different, I agree. I am not sure how much power they have. It seems like they can do a little more than a president can but I am not certain.\nChunk 3: Human: I saw the president of t...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I'm doing good thanks for asking. I think it's different. What about you?", "role": "user", "streaming_reasoning": "The user mentions asking for recommendations a...
{ "answer": "Lol! Well, I can they can do a bit more if they can give title's to their pets!", "reasoning": "The dialogue is about \"I'm doing good thanks for asking. I think it's different.\" The user later explains \"I saw the president of the UK has a cat with a government.\" The answer should treat this as a di...
{ "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_df181214-cdd8-4e54-b74d-746ae7116743", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002450
train
audio
multi_turn
[ { "role": "user", "text": "okay, r o e f.", "turn_id": 1 }, { "role": "assistant", "text": "okay, so i'm also looking for a train.", "turn_id": 2 }, { "role": "user", "text": "uh, yes, the choice should be on the same day as the restaurant booking and should go to cambridge."...
{ "chunk_text": "Chunk 1: okay, r o e f.\nChunk 2: okay, so i'm also looking for a train.\nChunk 3: uh, yes, the choice should be on the same day as the restaurant booking and should go to cambridge.\nChunk 4: ah the train should arrive by one quarter to 11 a m.\nChunk 5: yes, that's right. you're right.\nChunk 6: uh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, r o e f.", "role": "user", "streaming_reasoning": "The user mentions Okay, r o e f. It is not yet clear whether the user needs the full scope of the user's request...
{ "answer": "Sure. I can provide the id for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train. Key context: okay, r o e f; okay, so i'm also looking for a train; uh, yes, the choice should be on the same day as the restaurant booking and should go to cambridge; ah the t...
{ "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": "MUL1012", "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_002451
train
audio
multi_turn
[ { "role": "user", "text": "hello, i'm looking for an attraction.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for some kind of a gallery which is in a town area.", "turn_id": 2 }, { "role": "user", "text": "sure.", "turn_id": 3 }, { "role": "assis...
{ "chunk_text": "Chunk 1: hello, i'm looking for an attraction.\nChunk 2: i'm looking for some kind of a gallery which is in a town area.\nChunk 3: sure.\nChunk 4: okay. could you kindly provide me the address.\nChunk 5: okay, and the phone number, please.", "dialogue_text": "Chunk 1: hello, i'm looking for an attr...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, i'm looking for an attraction.", "role": "user", "streaming_reasoning": "The user mentions Hello, i'm looking for an attraction. It is not yet clear whether the u...
{ "answer": "Sure. I can provide the address, phone for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for attraction. Key context: hello, i'm looking for an attraction; i'm looking for some kind of a gallery which is in a town area; could you kindly provide me the addres...
{ "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": "MUL3467", "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_002452
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.", "dialogue...
{ "num_checkpoints": 5, "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": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: 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 the ex...
{ "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_002453
train
audio
multi_turn
[ { "role": "user", "text": "my name is leslie is.", "turn_id": 1 }, { "role": "assistant", "text": "okay, if. l e s t e r.", "turn_id": 2 }, { "role": "user", "text": "yes, you are correct.", "turn_id": 3 }, { "role": "assistant", "text": "and then m a y e f.",...
{ "chunk_text": "Chunk 1: my name is leslie is.\nChunk 2: okay, if. l e s t e r.\nChunk 3: yes, you are correct.\nChunk 4: and then m a y e f.\nChunk 5: yeah.\nChunk 6: uh, why do you need my email address.\nChunk 7: ah sorry, i don't prefer to give up my email address.\nChunk 8: uh, i'm also looking for a place to g...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "my name is leslie is.", "role": "user", "streaming_reasoning": "The user mentions My name is leslie is. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help with the attraction. Could you share the type?", "reasoning": "Across the dialogue, the user is searching for place to go in the west of cambridge. Key context: my name is leslie is; l e s t e r; yes, you are correct; and then m a y e f. The answer should focus on the latest user turn while ...
{ "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": "MUL1896", "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_002454
train
audio
multi_turn
[ { "role": "user", "text": "it should arrive at my destination by 1215, please.", "turn_id": 1 }, { "role": "assistant", "text": "from cambot, please.", "turn_id": 2 }, { "role": "user", "text": "it is all saints church.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: it should arrive at my destination by 1215, please.\nChunk 2: from cambot, please.\nChunk 3: it is all saints church.\nChunk 4: that is not a problem.\nChunk 5: is before.\nChunk 6: 1 for one.\nChunk 7: 1 62.\nChunk 8: can i get the car type, please.", "dialogue_text": "Chunk 1: it should ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "it should arrive at my destination by 1215, please.", "role": "user", "streaming_reasoning": "The user mentions It should arrive at my destination by 1215, please. It is...
{ "answer": "Sure. I can provide the car for the matching taxi option.", "reasoning": "Across the dialogue, the user is reporting a problem with it should arrive at my destination by 1215, please. Key context: it should arrive at my destination by 1215, please; from cambot, please; it is all saints church; that is ...
{ "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": "SNG1322", "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_000696
train
audio
multi_turn
[ { "role": "user", "text": "Human: Well they do take a lot of time to set up between plays, kickoffs, timeouts so I can see how there is only 11 minutes of actual action", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I enjoy the whole game. There is so much we can know about the...
{ "chunk_text": "Chunk 1: Human: Well they do take a lot of time to set up between plays, kickoffs, timeouts so I can see how there is only 11 minutes of actual action\nChunk 2: Assistant: I enjoy the whole game. There is so much we can know about the players because they are using tracking chips that they locate in ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Well they do take a lot of time to set up between plays, kickoffs, timeouts so I can see how there is only 11 minutes of actual action", "role": "user", "streamin...
{ "answer": "that makes it way more interesting, did you know the New Orleans Saints cheerleaders are forbidden from eating i the same restaurants as the players!! kind of crazy", "reasoning": "Across the dialogue, the user is searching for in the player's shoulder pads. Key context: Human: Well they do take a lot ...
{ "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_02722a25-ceef-47a5-8cea-205186520f9e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002455
train
audio
multi_turn
[ { "role": "user", "text": "the train should leave. no, wait. going to cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "on monday.", "turn_id": 2 }, { "role": "user", "text": "and should arrive in cambridge. um i have a one pm meeting, so maybe for 30 minutes earli...
{ "chunk_text": "Chunk 1: the train should leave. no, wait. going to cambridge.\nChunk 2: on monday.\nChunk 3: and should arrive in cambridge. um i have a one pm meeting, so maybe for 30 minutes earlier.\nChunk 4: yes, please.\nChunk 5: that rate like to book it for three people.\nChunk 6: my id is pray 8 9 0.\nChunk...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "the train should leave. no, wait. going to cambridge.", "role": "user", "streaming_reasoning": "The user mentions The train should leave. no, wait. going to cambridge. I...
{ "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 it for three people. Key context: the train should leave; going to cambridge; and should arrive in cambridge; um i have a one pm meeting, so may...
{ "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": "MUL3587", "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_002456
train
audio
multi_turn
[ { "role": "user", "text": "yes, please. it's 1 8. so did you get that.", "turn_id": 1 }, { "role": "assistant", "text": "4 2 6 did you get that.", "turn_id": 2 }, { "role": "user", "text": "and lastly, it's 9 9 total.", "turn_id": 3 }, { "role": "assistant", "...
{ "chunk_text": "Chunk 1: yes, please. it's 1 8. so did you get that.\nChunk 2: 4 2 6 did you get that.\nChunk 3: and lastly, it's 9 9 total.\nChunk 4: alright, thank you. can you please provide me with the car type of the taxi.\nChunk 5: oh, it's oh, okay, thank you.\nChunk 6: no, thank you.\nChunk 7: no, it's okay....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, please. it's 1 8. so did you get that.", "role": "user", "streaming_reasoning": "The user mentions Yes, please. it's 1 8. so did you get that. It is not yet clear w...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is talking about yes, please. Key context: yes, please; so did you get that; 4 2 6 did you get that; and lastly, it's 9 9 total. The answer should focus on the latest user turn while incorporating...
{ "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": "SNG0547", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002457
train
audio
multi_turn
[ { "role": "user", "text": "um the restaurant should serve north american food.", "turn_id": 1 }, { "role": "assistant", "text": "sure. i suppose the restaurant should be in downtown because i have many important things to do there.", "turn_id": 2 }, { "role": "user", "text": ...
{ "chunk_text": "Chunk 1: um the restaurant should serve north american food.\nChunk 2: sure. i suppose the restaurant should be in downtown because i have many important things to do there.\nChunk 3: well, i suppose it should be in the moderate price range and the. may i know. do you have any recommendation.\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um the restaurant should serve north american food.", "role": "user", "streaming_reasoning": "The user mentions Um the restaurant should serve north american food. It is...
{ "answer": "Sure. I can provide the phone for the matching restaurant option.", "reasoning": "Across the dialogue, the user is asking for recommendations about that. Key context: um the restaurant should serve north american food; i suppose the restaurant should be in downtown because i have many important things ...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "hard", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0598", "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_002458
train
audio
multi_turn
[ { "role": "user", "text": "i would like it to be a one star.", "turn_id": 1 }, { "role": "assistant", "text": "yes, that would be ok.", "turn_id": 2 }, { "role": "user", "text": "yes, i would like to bucket it.", "turn_id": 3 }, { "role": "assistant", "text": ...
{ "chunk_text": "Chunk 1: i would like it to be a one star.\nChunk 2: yes, that would be ok.\nChunk 3: yes, i would like to bucket it.\nChunk 4: one person, please.\nChunk 5: two nights. starting from.\nChunk 6: my apologies starting from the day after sunday.\nChunk 7: yes, i'm looking for more information.\nChunk 8...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i would like it to be a one star.", "role": "user", "streaming_reasoning": "The user mentions I would like it to be a one star. It is not yet clear whether the user need...
{ "answer": "I can help book that. Could you provide the departure, destination, time?", "reasoning": "Across the dialogue, the user is searching for more information. Key context: i would like it to be a one star; yes, that would be ok; yes, i would like to bucket it; one person, please. The answer should focus on...
{ "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": "MUL3365", "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_002459
train
audio
multi_turn
[ { "role": "user", "text": "ok, thank you.", "turn_id": 1 }, { "role": "assistant", "text": "okay, perfect. i'd also like to book a taxi. please, between the two places, the hotel and restaurant.", "turn_id": 2 }, { "role": "user", "text": "okay. can you make sure that it is a...
{ "chunk_text": "Chunk 1: ok, thank you.\nChunk 2: okay, perfect. i'd also like to book a taxi. please, between the two places, the hotel and restaurant.\nChunk 3: okay. can you make sure that it is a restaurant by the book.\nChunk 4: okay, and tell me what type of a car will this.\nChunk 5: oh, that's perfect. alrig...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "ok, thank you.", "role": "user", "streaming_reasoning": "The user mentions Ok, thank you. It is not yet clear whether the user needs the full scope of the user's request...
{ "answer": "Sure. I can provide the car for the matching taxi option.", "reasoning": "Across the dialogue, the user is wanting to book taxi. Key context: ok, thank you; okay, perfect; i'd also like to book a taxi; please, between the two places, the hotel and restaurant. The answer should focus on the latest user ...
{ "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": "MUL1306", "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_002460
train
audio
multi_turn
[ { "role": "user", "text": "yes, i'm looking for trends.", "turn_id": 1 }, { "role": "assistant", "text": "the treasury depart from cambridge.", "turn_id": 2 }, { "role": "user", "text": "and bang for where i leave it.", "turn_id": 3 }, { "role": "assistant", "...
{ "chunk_text": "Chunk 1: yes, i'm looking for trends.\nChunk 2: the treasury depart from cambridge.\nChunk 3: and bang for where i leave it.\nChunk 4: that's right.\nChunk 5: mm, i will leave on thursday.\nChunk 6: well, i suppose the train should arrive from a quarter to 4 p m.\nChunk 7: okay.\nChunk 8: mm. i think...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, i'm looking for trends.", "role": "user", "streaming_reasoning": "The user mentions Yes, i'm looking for trends. It is not yet clear whether the user needs the full...
{ "answer": "Sure. I can provide the id for the matching train option.", "reasoning": "Across the dialogue, the user is searching for trends. Key context: yes, i'm looking for trends; the treasury depart from cambridge; and bang for where i leave it; that's right. The answer should focus on the latest user turn whi...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0599", "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_002461
train
audio
multi_turn
[ { "role": "user", "text": "uh huh.", "turn_id": 1 }, { "role": "assistant", "text": "so will it will you be able to help and book it for me actually.", "turn_id": 2 }, { "role": "user", "text": "so my name is michael nixon.", "turn_id": 3 }, { "role": "assistant",...
{ "chunk_text": "Chunk 1: uh huh.\nChunk 2: so will it will you be able to help and book it for me actually.\nChunk 3: so my name is michael nixon.\nChunk 4: yes, m i c h a e l, michael.\nChunk 5: listen a i s o m.\nChunk 6: yes, that's correct.\nChunk 7: so can you. please try whether any available table for 8.\nChu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh huh.", "role": "user", "streaming_reasoning": "The user mentions Uh huh. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is wanting to book it for me actually. Key context: so will it will you be able to help and book it for me actually; so my name is michael nixon; yes, m i c h a e l, michael; listen a i s o m. T...
{ "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": "MUL1887", "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_000697
train
audio
multi_turn
[ { "role": "user", "text": "Human: No I didn't know that but it's a little funny to think about! Thinking about hockey from earlier I remembered that there's more than one type of hockey. Most of the planet thinks of hockey as f", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Tru...
{ "chunk_text": "Chunk 1: Human: No I didn't know that but it's a little funny to think about! Thinking about hockey from earlier I remembered that there's more than one type of hockey. Most of the planet thinks of hockey as field hockey whereas Canada and the U.S. think of it as ice hockey.\nChunk 2: Assistant: True...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: No I didn't know that but it's a little funny to think about! Thinking about hockey from earlier I remembered that there's more than one type of hockey. Most of the planet th...
{ "answer": "wow! Hockey also only had 1 shared penalty box! Imagine the fights!", "reasoning": "Across the dialogue, the user is asking for help with human: no i didn't know that but it's a little funny to think about. Key context: Human: No I didn't know that but it's a little funny to think about; Thinking about...
{ "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_a44c497a-03a8-44e4-95f1-6442e1a5d09d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002462
train
audio
multi_turn
[ { "role": "user", "text": "alright, so i would like to book for my sister and myself for two.", "turn_id": 1 }, { "role": "assistant", "text": "yes, please.", "turn_id": 2 }, { "role": "user", "text": "from friday.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: alright, so i would like to book for my sister and myself for two.\nChunk 2: yes, please.\nChunk 3: from friday.\nChunk 4: yes, my name is amber johnson. and the spelling of my name is a m.\nChunk 5: b er.\nChunk 6: and my surname is j o h.\nChunk 7: n s.\nChunk 8: and or am.", "dialogue_t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "alright, so i would like to book for my sister and myself for two.", "role": "user", "streaming_reasoning": "The user mentions wanting to book Alright. 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 for my sister. Key context: alright, so i would like to book for my sister and myself for two; yes, please; from friday; yes, my name is amber johnson. The answer should...
{ "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": "MUL0411", "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_002463
train
audio
multi_turn
[ { "role": "user", "text": "um, it's 2 8 5. did you get that.", "turn_id": 1 }, { "role": "assistant", "text": "5 6 0. did you get that.", "turn_id": 2 }, { "role": "user", "text": "and last week it's 7 9 4.", "turn_id": 3 }, { "role": "assistant", "text": "oka...
{ "chunk_text": "Chunk 1: um, it's 2 8 5. did you get that.\nChunk 2: 5 6 0. did you get that.\nChunk 3: and last week it's 7 9 4.\nChunk 4: okay um thank you i would also like to book a taxi to commit me from the restaurant of the hotel and it should depart\nChunk 5: by seven thirty pm\nChunk 6: okay. can you please...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um, it's 2 8 5. did you get that.", "role": "user", "streaming_reasoning": "The user mentions Um, it's 2 8 5. did you get that. It is not yet clear whether the user need...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is wanting to book taxi to commit me from the restaurant of the hotel. Key context: um, it's 2 8 5; did you get that; did you get that; and last week it's 7 9 4. The answer should focus on the lat...
{ "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": "MUL1273", "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_002464
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "ya um so i'm looking for a place to stay uh it should include free parking and it should be a two star uh hotel", "turn_id": 2 }, { "role": "user", "text": "in the north", "turn_id"...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: ya um so i'm looking for a place to stay uh it should include free parking and it should be a two star uh hotel\nChunk 3: in the north\nChunk 4: okay. um which one is cheaper for a double room.\nChunk 5: alright, then let's go for the lovell lodge. um i like to book f...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "I can help book that. Could you provide the price, day?", "reasoning": "Across the dialogue, the user is searching for place to stay uh it should include free parking. Key context: ya um so i'm looking for a place to stay uh it should include free parking and it should be a two star uh hotel in the nor...
{ "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": "MUL3225", "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_002465
train
audio
multi_turn
[ { "role": "user", "text": "9 2 1.", "turn_id": 1 }, { "role": "assistant", "text": "0, 1, 2.", "turn_id": 2 }, { "role": "user", "text": "0 1 8.", "turn_id": 3 }, { "role": "assistant", "text": "9 4 5 1.", "turn_id": 4 }, { "role": "user", "tex...
{ "chunk_text": "Chunk 1: 9 2 1.\nChunk 2: 0, 1, 2.\nChunk 3: 0 1 8.\nChunk 4: 9 4 5 1.\nChunk 5: yes.\nChunk 6: okay, i'm actually looking for a restaurant in a cheap price range growing french food and dealing with some foie.\nChunk 7: ok, thank you.\nChunk 8: it could be in any area.", "dialogue_text": "Chunk 1:...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "9 2 1.", "role": "user", "streaming_reasoning": "The user mentions 9 2 1. 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?", "reasoning": "Across the dialogue, the user is searching for restaurant in a cheap price range growing french food. Key context: okay, i'm actually looking for a restaurant in a cheap price range growing french food and dealing with some foie;...
{ "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": "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_002466
train
audio
multi_turn
[ { "role": "user", "text": "from my house cafe, please.", "turn_id": 1 }, { "role": "assistant", "text": "hoping. but so sorry from my hippie, sorry.", "turn_id": 2 }, { "role": "user", "text": "mike and i was cafe.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: from my house cafe, please.\nChunk 2: hoping. but so sorry from my hippie, sorry.\nChunk 3: mike and i was cafe.\nChunk 4: uh, i like to live after 12. uh, pay at least an hour before a topic of this.\nChunk 5: ok, thank you for that.\nChunk 6: my telephone number is 9 6 1 8 double 9 8 7 dou...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "from my house cafe, please.", "role": "user", "streaming_reasoning": "The user mentions From my house cafe, please. It is not yet clear whether the user needs the timing...
{ "answer": "I can help find a matching taxi option with those details.", "reasoning": "Across the dialogue, the user is talking about from my house cafe, please. Key context: from my house cafe, please; but so sorry from my hippie, sorry; mike and i was cafe; uh, i like to live after 12. The answer should focus on...
{ "category": "daily_life", "subcategory": "personal_preference", "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": "SNG1523", "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_002467
train
audio
multi_turn
[ { "role": "user", "text": "hmm, got that. thank you.", "turn_id": 1 }, { "role": "assistant", "text": "sure, i was looking for a train.", "turn_id": 2 }, { "role": "user", "text": "um i think the trend should live on this monday.", "turn_id": 3 }, { "role": "assis...
{ "chunk_text": "Chunk 1: hmm, got that. thank you.\nChunk 2: sure, i was looking for a train.\nChunk 3: um i think the trend should live on this monday.\nChunk 4: right monday.\nChunk 5: and should depart from. depart from cambridge.\nChunk 6: i'm going to knowledge.\nChunk 7: right.\nChunk 8: mm i have a i have a i...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hmm, got that. thank you.", "role": "user", "streaming_reasoning": "The user mentions Hmm, got that. thank you. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help with the train. Could you share the day?", "reasoning": "Across the dialogue, the user is searching for train. Key context: hmm, got that; sure, i was looking for a train; um i think the trend should live on this monday; right monday. The answer should focus on the latest user turn while inc...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "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_spokenwoz_v02_002468
train
audio
multi_turn
[ { "role": "user", "text": "okay, great. thank you.", "turn_id": 1 }, { "role": "assistant", "text": "hello.", "turn_id": 2 }, { "role": "user", "text": "and i wanted to depart from cambridge.", "turn_id": 3 }, { "role": "assistant", "text": "uh, also the train...
{ "chunk_text": "Chunk 1: okay, great. thank you.\nChunk 2: hello.\nChunk 3: and i wanted to depart from cambridge.\nChunk 4: uh, also the train should arrive. 1313.\nChunk 5: also, i wanted to go to stimulate.\nChunk 6: uh, actually it's arrive by 13.\nChunk 7: okay, i wanted to know the travel time.\nChunk 8: okay,...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, great. thank you.", "role": "user", "streaming_reasoning": "The user mentions Okay, great. thank you. It is not yet clear whether the user needs the full scope of ...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: okay, great; and i wanted to depart from cambridge; uh, also the train should arrive; also, i wanted to go to stimulate. The answer should focus on ...
{ "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": "MUL0381", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002469
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "and thanks for yourself.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a place to dine.", "turn_id": 3 }, { "role": "assistant", "text": "breast trend should be ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: and thanks for yourself.\nChunk 3: i'm looking for a place to dine.\nChunk 4: breast trend should be in the north of cambridge and should save international.\nChunk 5: i am no, no, no.\nChunk 6: okay. how about one that serves indian food.", "dialogue_text": "Chunk 1: hell...
{ "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 with the restaurant. Could you share the price?", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: and thanks for yourself; i'm looking for a place to dine; breast trend should be in the north of cambridge and should save international; i am no, no, no...
{ "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": "MUL2040", "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_002470
train
audio
multi_turn
[ { "role": "user", "text": "what about one that has british routine.", "turn_id": 1 }, { "role": "assistant", "text": "okay, perfect. i'd like to make a booking, please.", "turn_id": 2 }, { "role": "user", "text": "it would be for myself and my husband.", "turn_id": 3 },...
{ "chunk_text": "Chunk 1: what about one that has british routine.\nChunk 2: okay, perfect. i'd like to make a booking, please.\nChunk 3: it would be for myself and my husband.\nChunk 4: this would be. sure. so our wedding anniversary is on sunday. but he's not home. so after sunday.\nChunk 5: yes. i think there's a ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "what about one that has british routine.", "role": "user", "streaming_reasoning": "The user mentions What about one that has british routine. It is not yet clear whether...
{ "answer": "I can help book that. Could you provide the area, price, time?", "reasoning": "Across the dialogue, the user is wanting to book what about one that has british routine. Key context: what about one that has british routine; okay, perfect; i'd like to make a booking, please; it would be for myself and my...
{ "category": "daily_life", "subcategory": "shopping_decision", "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": "SpokenWOZ", "dialogue_id": "MUL3557", "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_002471
train
audio
multi_turn
[ { "role": "user", "text": "good evening, ma'am. hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes. are you looking for an expensive restaurant in the city center, 7 british food.", "turn_id": 2 }, { "role": "user", "text": "yes.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: good evening, ma'am. hello.\nChunk 2: yes. are you looking for an expensive restaurant in the city center, 7 british food.\nChunk 3: yes.", "dialogue_text": "Chunk 1: good evening, ma'am. hello.\nChunk 2: yes. are you looking for an expensive restaurant in the city center, 7 british food.\...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "good evening, ma'am. hello.", "role": "user", "streaming_reasoning": "The user mentions Good evening, ma'am. hello. It is not yet clear whether the user needs the full s...
{ "answer": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for expensive restaurant in the city center. Key context: good evening, ma'am; are you looking for an expensive restaurant in the city center, 7 british food. The answer should fo...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0630", "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_002472
train
audio
multi_turn
[ { "role": "user", "text": "hi, it's a customer service.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a restaurant in cambridge.", "turn_id": 2 }, { "role": "user", "text": "yes, i want to have cheap portuguese food.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hi, it's a customer service.\nChunk 2: yes, i'm looking for a restaurant in cambridge.\nChunk 3: yes, i want to have cheap portuguese food.", "dialogue_text": "Chunk 1: hi, it's a customer service.\nChunk 2: yes, i'm looking for a restaurant in cambridge.\nChunk 3: yes, i want to have chea...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, it's a customer service.", "role": "user", "streaming_reasoning": "The user mentions Hi, it's a customer service. It is not yet clear whether the user needs the full...
{ "answer": "I can help with the restaurant. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for restaurant in cambridge. Key context: hi, it's a customer service; yes, i'm looking for a restaurant in cambridge; yes, i want to have cheap portuguese food. The answer should focus ...
{ "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": "MUL1903", "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_002473
train
audio
multi_turn
[ { "role": "user", "text": "can. all right, perfect. can i please also make a booking then.", "turn_id": 1 }, { "role": "assistant", "text": "um just for myself.", "turn_id": 2 }, { "role": "user", "text": "well, i've got five days leave and i need to be home on austin.", ...
{ "chunk_text": "Chunk 1: can. all right, perfect. can i please also make a booking then.\nChunk 2: um just for myself.\nChunk 3: well, i've got five days leave and i need to be home on austin.\nChunk 4: yes, please.\nChunk 5: from monday.\nChunk 6: yes. so my first name is jason.\nChunk 7: hamilton.\nChunk 8: yes. w...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "can. all right, perfect. can i please also make a booking then.", "role": "user", "streaming_reasoning": "The user mentions Can. It is not yet clear whether the user nee...
{ "answer": "I can help with the restaurant. Could you share the food, price?", "reasoning": "Across the dialogue, the user is wanting to book to be home on austin. Key context: all right, perfect; can i please also make a booking then; um just for myself; well, i've got five days leave and i need to be home on aus...
{ "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": "MUL3543", "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_002474
train
audio
multi_turn
[ { "role": "user", "text": "who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm telling you what to do. can you help me.", "turn_id": 1 }, { "role": "assistant", "text": "i am looking for a train.", "turn_id": 2 }, { "role": "user", "tex...
{ "chunk_text": "Chunk 1: who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm telling you what to do. can you help me.\nChunk 2: i am looking for a train.\nChunk 3: the train will be going into peter borough.", "dialogue_text": "Chunk 1: who. hello, you speaking with philip a...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm telling you what to do. can you help me.", "role": "user", "streaming_reasoni...
{ "answer": "I can help with the train. Could you share the departure, day, time?", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: hello, you speaking with philip and i'm looking for some information in cambridge; i'm telling you what to do; can you help me; i am...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0628", "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_000698
train
audio
multi_turn
[ { "role": "user", "text": "Human: Ya and unlike other sports, being a lefty QB has more cons than pro", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Wow, didn't realize that. Speaking of hands, did you know that former Patriots RB Benjarvus Green-Ellis has never fumbled the foo...
{ "chunk_text": "Chunk 1: Human: Ya and unlike other sports, being a lefty QB has more cons than pro\nChunk 2: Assistant: Wow, didn't realize that. Speaking of hands, did you know that former Patriots RB Benjarvus Green-Ellis has never fumbled the football in his NFL career? Wow.\nChunk 3: Human: That is indeed impre...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Ya and unlike other sports, being a lefty QB has more cons than pro", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not yet...
{ "answer": "Another lesser known fact about football is the highest score ever in a football game occurred in 1916 when Georgia Tech defeated Cumberland 222 to 0. Wow, unbelievable.", "reasoning": "Across the dialogue, the user discusses \"Ya and unlike other sports, being a lefty QB has more cons.\" over 3 turns....
{ "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_568ede67-ac2b-4457-9b08-74fa33bcab10", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002475
train
audio
multi_turn
[ { "role": "user", "text": "uh, a guest house will be wonderful.", "turn_id": 1 }, { "role": "assistant", "text": "yes. uh, if the hotel have including free wi fi. it will be fine.", "turn_id": 2 }, { "role": "user", "text": "i'd like to stay in the west.", "turn_id": 3 ...
{ "chunk_text": "Chunk 1: uh, a guest house will be wonderful.\nChunk 2: yes. uh, if the hotel have including free wi fi. it will be fine.\nChunk 3: i'd like to stay in the west.\nChunk 4: yes, please make a book for seven people.\nChunk 5: uh, we will check in on friday.\nChunk 6: i think we will stay there for five...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, a guest house will be wonderful.", "role": "user", "streaming_reasoning": "The user mentions Uh, a guest house will be wonderful. It is not yet clear whether the use...
{ "answer": "I can help book that. Could you provide the price?", "reasoning": "Across the dialogue, the user is wanting to book for seven people. Key context: uh, a guest house will be wonderful; uh, if the hotel have including free wi fi; it will be fine; i'd like to stay in the west. The answer should focus on 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": "MUL2295", "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_002476
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "good day. i'm looking for information. i want to turn in cambridge.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train that leaves on wednesday and arrives by 11 a. m..", ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: good day. i'm looking for information. i want to turn in cambridge.\nChunk 3: i'm looking for a train that leaves on wednesday and arrives by 11 a. m..\nChunk 4: question. and you should depart from cambridge and go to london, give a quick.", "dialogue_text": "Chunk 1: hel...
{ "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 find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for information. Key context: i'm looking for information; i want to turn in cambridge; i'm looking for a train that leaves on wednesday and arrives by 11 a; and you should depart from...
{ "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": "MUL2641", "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_002477
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "um this is jeremy johnson. am i free to get the messages.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a place to stay.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: um this is jeremy johnson. am i free to get the messages.\nChunk 3: i'm looking for a place to stay.\nChunk 4: and cambridge.\nChunk 5: mm. moderate price range.\nChunk 6: informant will be fine.\nChunk 7: yes.", "dialogue_text": "Chunk 1: hello.\nChunk 2: um this is jerem...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the hotel. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: um this is jeremy johnson; am i free to get the messages; i'm looking for a place to stay; and cambridge. The answer should focus on the latest user turn while...
{ "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": "MUL2883", "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_000699
train
audio
multi_turn
[ { "role": "user", "text": "Human: I use to wear Aladdin's pants after mc hammer.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Nice! It was illegal for women to wear pants in Paris until 2013. Say what? So unfair. It was like that for 200 years.", "turn_id": 2 }, { ...
{ "chunk_text": "Chunk 1: Human: I use to wear Aladdin's pants after mc hammer.\nChunk 2: Assistant: Nice! It was illegal for women to wear pants in Paris until 2013. Say what? So unfair. It was like that for 200 years.\nChunk 3: Human: I could not live there at all. all I wear is pants for work.Listen to this, A d.c...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I use to wear Aladdin's pants after mc hammer.", "role": "user", "streaming_reasoning": "The user mentions Human: I use to wear Aladdin's pants after mc hammer. I...
{ "answer": "Yeah me either. That is crazy. Must have been some pair of pant (maybe Hulk's) lol.", "reasoning": "Across the dialogue, the user is asking for help with human: i use to wear aladdin's pants after mc hammer. Key context: Human: I use to wear Aladdin's pants after mc hammer; Assistant: Nice; It was ille...
{ "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_2598a9a2-3287-4fc2-ad02-ec8e65687c8b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002478
train
audio
multi_turn
[ { "role": "user", "text": "which info do you need.", "turn_id": 1 }, { "role": "assistant", "text": "this will be on saturday at. 1015 then.", "turn_id": 2 }, { "role": "user", "text": "my name is spelt ca ha r. le f, charles.", "turn_id": 3 }, { "role": "assistan...
{ "chunk_text": "Chunk 1: which info do you need.\nChunk 2: this will be on saturday at. 1015 then.\nChunk 3: my name is spelt ca ha r. le f, charles.\nChunk 4: it is about y ou ng young.\nChunk 5: email won't be necessary.\nChunk 6: yes, you may please.\nChunk 7: please help me find a nice attraction also in the cen...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "which info do you need.", "role": "user", "streaming_reasoning": "The user mentions Which info do you need. It is not yet clear whether the user needs the full scope of ...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for which info do you need. Key context: which info do you need; this will be on saturday at; my name is spelt ca ha r; le f, charles. The answer should focus on the latest user t...
{ "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": "MUL3796", "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_002479
train
audio
multi_turn
[ { "role": "user", "text": "okay.", "turn_id": 1 }, { "role": "assistant", "text": "mm. i think that's ok.", "turn_id": 2 }, { "role": "user", "text": "yes. um, i'm looking for some information of that.", "turn_id": 3 }, { "role": "assistant", "text": "okay. ok...
{ "chunk_text": "Chunk 1: okay.\nChunk 2: mm. i think that's ok.\nChunk 3: yes. um, i'm looking for some information of that.\nChunk 4: okay. okay. um, may i know the address.\nChunk 5: hmm.\nChunk 6: yeah, i also need the postcode of the the attraction.\nChunk 7: got it. thank you so much.\nChunk 8: sure. mm. i'm al...
{ "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 with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for information of that. Key context: i think that's ok; um, i'm looking for some information of that; um, may i know the address; yeah, i also need the postcode of the...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0338", "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_002480
train
audio
multi_turn
[ { "role": "user", "text": "yes, please, i am looking for a train.", "turn_id": 1 }, { "role": "assistant", "text": "i'm going from cambridge to stanford airport.", "turn_id": 2 }, { "role": "user", "text": "oh, yes to cambridge from stanford airport.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: yes, please, i am looking for a train.\nChunk 2: i'm going from cambridge to stanford airport.\nChunk 3: oh, yes to cambridge from stanford airport.\nChunk 4: so i need to arrive in cambridge by latest quarter to 9 in the evening.\nChunk 5: and that would be. the.\nChunk 6: day before friday...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, please, i am looking for a train.", "role": "user", "streaming_reasoning": "The user mentions Yes, please, i am looking for a train. It is not yet clear whether the...
{ "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: yes, please, i am looking for a train; i'm going from cambridge to stanford airport; oh, yes to cambridge from stanford airpor...
{ "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": "MUL2015", "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_002481
train
audio
multi_turn
[ { "role": "user", "text": "yes, sure. please. i want to find an attraction that is in the east part of cambridge, can you help me.", "turn_id": 1 }, { "role": "assistant", "text": "yes.", "turn_id": 2 }, { "role": "user", "text": "cambodia sounds good. can you tell me when do...
{ "chunk_text": "Chunk 1: yes, sure. please. i want to find an attraction that is in the east part of cambridge, can you help me.\nChunk 2: yes.\nChunk 3: cambodia sounds good. can you tell me when does it open.\nChunk 4: okay. and do i need to pay for the ticket.\nChunk 5: okay i got that and the i also want to find...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, sure. please. i want to find an attraction that is in the east part of cambridge, can you help me.", "role": "user", "streaming_reasoning": "The user mentions Yes, ...
{ "answer": "I can help with the hotel. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for to find an attraction that is in the east part of cambridge. Key context: i want to find an attraction that is in the east part of cambridge, can you help me; cambodia sounds good; can yo...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1244", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000700
train
audio
multi_turn
[ { "role": "user", "text": "Human: yep. The nfl has no written rule against female players; women would in fact be allowed if they met the league's eligibility requirements. I wonder if there will ever be a female player anytime", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: tha...
{ "chunk_text": "Chunk 1: Human: yep. The nfl has no written rule against female players; women would in fact be allowed if they met the league's eligibility requirements. I wonder if there will ever be a female player anytime soon\nChunk 2: Assistant: that would be fun. It would have to be a very strong one. and I f...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: yep. The nfl has no written rule against female players; women would in fact be allowed if they met the league's eligibility requirements. I wonder if there will ever be a fe...
{ "answer": "I enjoy the whole game. There is so much we can know about the players because they are using tracking chips that they locate in the player's shoulder pads.", "reasoning": "Across the dialogue, the user is asking for help with the nfl has no written rule against female players; women would in fact be a...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_02722a25-ceef-47a5-8cea-205186520f9e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002482
train
audio
multi_turn
[ { "role": "user", "text": "um, yes, how about one that serves portuguese food.", "turn_id": 1 }, { "role": "assistant", "text": "that's great.", "turn_id": 2 }, { "role": "user", "text": "yes, please, i'd like to book a table for five people. for quarter to one pm on a thursd...
{ "chunk_text": "Chunk 1: um, yes, how about one that serves portuguese food.\nChunk 2: that's great.\nChunk 3: yes, please, i'd like to book a table for five people. for quarter to one pm on a thursday today. so for tomorrow.\nChunk 4: at a restaurant. for five.\nChunk 5: yes.\nChunk 6: gotta talk great.\nChunk 7: m...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um, yes, how about one that serves portuguese food.", "role": "user", "streaming_reasoning": "The user mentions Um, yes, how about one that serves portuguese food. It is...
{ "answer": "I can help book that. Could you provide the area, price?", "reasoning": "Across the dialogue, the user is wanting to book table for five people. Key context: um, yes, how about one that serves portuguese food; that's great; yes, please, i'd like to book a table for five people; for quarter to one pm 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": "MUL3577", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002483
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i don't much. yes.", "turn_id": 2 }, { "role": "user", "text": "i would just make sure that i don't have to wait.", "turn_id": 3 }, { "role": "assistant", "text": "yes.", "...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i don't much. yes.\nChunk 3: i would just make sure that i don't have to wait.\nChunk 4: yes.\nChunk 5: yeah. that will be perfect.\nChunk 6: yeah.\nChunk 7: okay, my phone number is 0 9.\nChunk 8: mindset.", "dialogue_text": "Chunk 1: hello.\nChunk 2: i don't much. yes.\n...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the taxi. Could you share the departure, destination?", "reasoning": "Across the dialogue, the user is talking about i don't much. Key context: i don't much; i would just make sure that i don't have to wait; that will be perfect; okay, my phone number is 0 9. The answer should focus on ...
{ "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": "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_spokenwoz_v02_002484
train
audio
multi_turn
[ { "role": "user", "text": "and lens. and then follows field.", "turn_id": 1 }, { "role": "assistant", "text": "okay, thank you.", "turn_id": 2 }, { "role": "user", "text": "yes, i would love to know about their. stars.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: and lens. and then follows field.\nChunk 2: okay, thank you.\nChunk 3: yes, i would love to know about their. stars.\nChunk 4: ok, thank you.\nChunk 5: okay, it sounds great.\nChunk 6: yes. what about their area.\nChunk 7: okay, great. thank you.\nChunk 8: uh, booking on the telephone will b...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and lens. and then follows field.", "role": "user", "streaming_reasoning": "The user mentions And lens. and then follows field. It is not yet clear whether the user need...
{ "answer": "Sure. I can provide the stars, area for the matching hotel option.", "reasoning": "Across the dialogue, the user is wanting to book and then follows field. Key context: and then follows field; okay, thank you; yes, i would love to know about their; ok, thank you. The answer should focus on the latest u...
{ "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": "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_002485
train
audio
multi_turn
[ { "role": "user", "text": "hello, could you help me.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a restaurant.", "turn_id": 2 }, { "role": "user", "text": "yes, i prefer the expensive price range.", "turn_id": 3 }, { "role": "assistant",...
{ "chunk_text": "Chunk 1: hello, could you help me.\nChunk 2: yes, i'm looking for a restaurant.\nChunk 3: yes, i prefer the expensive price range.\nChunk 4: and i think i want. the, uh, restaurant could have the very convenient traffic.\nChunk 5: no, for now this will be all.\nChunk 6: great. excellent. could you pl...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, could you help me.", "role": "user", "streaming_reasoning": "The user mentions Hello, could you help me. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help with the restaurant. Could you share the food?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: hello, could you help me; yes, i'm looking for a restaurant; yes, i prefer the expensive price range; and i think i want. The answer should focus on the late...
{ "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": "MUL1031", "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_002486
train
audio
multi_turn
[ { "role": "user", "text": "sure.", "turn_id": 1 }, { "role": "assistant", "text": "does that serve chinese food.", "turn_id": 2 }, { "role": "user", "text": "i see. okay. uh, could you help me book a table for. 8. people.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: sure.\nChunk 2: does that serve chinese food.\nChunk 3: i see. okay. uh, could you help me book a table for. 8. people.\nChunk 4: uh, on wednesday at 8 pm, please.\nChunk 5: sure, thanks.\nChunk 6: sure. can i book it for seven pm instead.\nChunk 7: yes, that's correct.\nChunk 8: my name is ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "sure.", "role": "user", "streaming_reasoning": "The user mentions Sure. It is not yet clear whether the user needs the full scope of the user's request. The assistant sh...
{ "answer": "I can help book that. Could you provide the area, price?", "reasoning": "The dialogue is about \"sure.\" The user later explains \"yes, that's correct.\" The answer should treat this as a discussion of the topic, not as a task-planning request.", "response": "Reasoning: The dialogue is about \"sure.\...
{ "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": "MUL3467", "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_000701
train
audio
multi_turn
[ { "role": "user", "text": "Human: Me too. The emperor of Japan is a scientist and still publishes papers to this day. I think he will catch up to the black panther shortly.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: True! I really like the director of Black Panther, Ryan Co...
{ "chunk_text": "Chunk 1: Human: Me too. The emperor of Japan is a scientist and still publishes papers to this day. I think he will catch up to the black panther shortly.\nChunk 2: Assistant: True! I really like the director of Black Panther, Ryan Coogler he did an amazing job!\nChunk 3: Human: He did a great job. I...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Me too. The emperor of Japan is a scientist and still publishes papers to this day. I think he will catch up to the black panther shortly.", "role": "user", "stre...
{ "answer": "Really? That's interesting! I didn't know that.", "reasoning": "Across the dialogue, the user is asking for help with nsibdi. Key context: Human: Me too; The emperor of Japan is a scientist and still publishes papers to this day; I think he will catch up to the black panther shortly; Assistant: True. T...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_80cd2d93-42df-4474-8149-1c1e7027ee16", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002487
train
audio
multi_turn
[ { "role": "user", "text": "was it. okay. how about one that is in the opposite to the south.", "turn_id": 1 }, { "role": "assistant", "text": "ashley.", "turn_id": 2 }, { "role": "user", "text": "okay, i'll do with it.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: was it. okay. how about one that is in the opposite to the south.\nChunk 2: ashley.\nChunk 3: okay, i'll do with it.\nChunk 4: yes, i want i want to put it for me. and four friends. over two nights starting from wednesday.\nChunk 5: my name is dean flory.\nChunk 6: the parade members as.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "was it. okay. how about one that is in the opposite to the south.", "role": "user", "streaming_reasoning": "The user mentions Was it. It is not yet clear whether the use...
{ "answer": "I can help with the hotel. Could you share the price, hotel_type?", "reasoning": "Across the dialogue, the user is talking about i want to put it for me. Key context: how about one that is in the opposite to the south; okay, i'll do with it; yes, i want i want to put it for me; and four friends. The an...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2310", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000702
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah, i bet the coaches want to know how the players are moving.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That's probably true. Did you know Kellan Moore is the only lefty in the game?", "turn_id": 2 }, { "role": "user", "...
{ "chunk_text": "Chunk 1: Human: Yeah, i bet the coaches want to know how the players are moving.\nChunk 2: Assistant: That's probably true. Did you know Kellan Moore is the only lefty in the game?\nChunk 3: Human: That seems odd. Why only one? do coaches dislike lefties?", "dialogue_text": "Chunk 1: Human: Yeah, i...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah, i bet the coaches want to know how the players are moving.", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Yeah. It is not ...
{ "answer": "It might be easier to set the offense up with righties. Anyways, nice chatting with you!", "reasoning": "Across the dialogue, the user discusses \"Yeah, i bet the coaches want to know how the players are.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conve...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "explain_cause" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_731a5255-cce7-42d0-a50f-630cec11d994", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002488
train
audio
multi_turn
[ { "role": "user", "text": "uh.", "turn_id": 1 }, { "role": "assistant", "text": "okay, then do you know about their address entrance c and open hours.", "turn_id": 2 }, { "role": "user", "text": "hello.", "turn_id": 3 }, { "role": "assistant", "text": "yes, i'...
{ "chunk_text": "Chunk 1: uh.\nChunk 2: okay, then do you know about their address entrance c and open hours.\nChunk 3: hello.\nChunk 4: yes, i'm looking for a train depart from cambridge.", "dialogue_text": "Chunk 1: uh.\nChunk 2: okay, then do you know about their address entrance c and open hours.\nChunk 3: hell...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh.", "role": "user", "streaming_reasoning": "The user mentions Uh. It is not yet clear whether the user needs the full scope of the user's request. The assistant should...
{ "answer": "I can help with the train. Could you share the destination, day, time?", "reasoning": "Across the dialogue, the user is searching for train depart from cambridge. Key context: okay, then do you know about their address entrance c and open hours; yes, i'm looking for a train depart from cambridge. The a...
{ "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": "MUL0382", "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_002489
train
audio
multi_turn
[ { "role": "user", "text": "hi, can you hear me.", "turn_id": 1 }, { "role": "assistant", "text": "oh, thank god. i think i was robbed and i'm looking for help. can you help me find the nearest polish.", "turn_id": 2 }, { "role": "user", "text": "oh, yes, it. oh, no, it's 0 6,...
{ "chunk_text": "Chunk 1: hi, can you hear me.\nChunk 2: oh, thank god. i think i was robbed and i'm looking for help. can you help me find the nearest polish.\nChunk 3: oh, yes, it. oh, no, it's 0 6, 0, 8.\nChunk 4: double 9 4 9 5 4.\nChunk 5: um yes, please tell me the phone number and the address of the playstatio...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, can you hear me.", "role": "user", "streaming_reasoning": "The user mentions Hi, can you hear me. It is not yet clear whether the user needs the full scope of the us...
{ "answer": "Sure. I can help with the phone, address; first I need to identify the right police option.", "reasoning": "Across the dialogue, the user is searching for help. Key context: hi, can you hear me; oh, thank god; i think i was robbed and i'm looking for help; can you help me find the nearest polish. The a...
{ "category": "social_communication", "subcategory": "conflict_deescalation", "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": "SNG0720", "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_002490
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for information in cambridge.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "have to go. to...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm looking for information in cambridge.\nChunk 3: i'm looking for a train.\nChunk 4: have to go. to replace, we are seeking information. and the train should depart from knowledge.\nChunk 5: today and leave after um 1414.\nChunk 6: you have to book for seven people.", "d...
{ "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 book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: i'm looking for information in cambridge; i'm looking for a train; to replace, we are seeking information; ...
{ "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": "MUL0830", "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_000703
train
audio
multi_turn
[ { "role": "user", "text": "Human: hello how are you?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Good how are you? Do you like horror films?", "turn_id": 2 }, { "role": "user", "text": "Human: I do I did not know it exsisted for over a century", "turn_id"...
{ "chunk_text": "Chunk 1: Human: hello how are you?\nChunk 2: Assistant: Good how are you? Do you like horror films?\nChunk 3: Human: I do I did not know it exsisted for over a century", "dialogue_text": "Chunk 1: Human: hello how are you?\nChunk 2: Assistant: Good how are you? Do you like horror films?\nChunk 3: H...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: hello how are you?", "role": "user", "streaming_reasoning": "The user mentions Human: hello how are you?. It is not yet clear whether the user needs what specific...
{ "answer": "Surprising that ET was originally supposed to be a horror movie", "reasoning": "Across the dialogue, the user discusses \"hello how are you?\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue,...
{ "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_a4c9f20d-f843-410d-ad31-e731b05e2222", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002491
train
audio
multi_turn
[ { "role": "user", "text": "can you please provide me with the phone number. of the hot sale restaurant.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i did.", "turn_id": 2 }, { "role": "user", "text": "3 3, 2 yes, i did.", "turn_id": 3 }, { "role": "assis...
{ "chunk_text": "Chunk 1: can you please provide me with the phone number. of the hot sale restaurant.\nChunk 2: yes, i did.\nChunk 3: 3 3, 2 yes, i did.\nChunk 4: yes, i did. thank you. can you also please provide me with the address of the restaurant.\nChunk 5: oh, okay. thank you. i would also like to book in a ho...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "can you please provide me with the phone number. of the hot sale restaurant.", "role": "user", "streaming_reasoning": "The user mentions Can you please provide me with t...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book in a hotel called ashley hotel. Key context: can you please provide me with the phone number; of the hot sale restaurant; 3 3, 2 yes, i did; can you also please provide ...
{ "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": "MUL1273", "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_000704
train
audio
multi_turn
[ { "role": "user", "text": "Human: Michael Phelps", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I saw him in the Ellen DeGeneres show. He was teaching Andy how to swim.", "turn_id": 2 }, { "role": "user", "text": "Human: That was cool. Do you know that native am...
{ "chunk_text": "Chunk 1: Human: Michael Phelps\nChunk 2: Assistant: I saw him in the Ellen DeGeneres show. He was teaching Andy how to swim.\nChunk 3: Human: That was cool. Do you know that native americans introduced the front crawl swimming to the west?", "dialogue_text": "Chunk 1: Human: Michael Phelps\nChunk 2...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Michael Phelps", "role": "user", "streaming_reasoning": "The user mentions Human: Michael Phelps. It is not yet clear whether the user needs the full scope of the...
{ "answer": "What is the front crawl swimming?", "reasoning": "Across the dialogue, the user discusses \"Michael Phelps\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user discusses \"Michael Phel...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "medium", "intent_type": "how_to_guide" }
{ "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_c011c3b8-1f88-43d8-895d-a9b26692777a", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002492
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "good day. i'm looking for information in cambridge. i want a place to stay.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: good day. i'm looking for information in cambridge. i want a place to stay.", "dialogue_text": "Chunk 1: hello. hello.\nChunk 2: good day. i'm looking for information in cambridge. i want a place to stay.", "instruction": "Help the user complete a spoken task-orie...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: i'm looking for information in cambridge; i want a place to stay. The answer should focus on the latest user turn while incorporating relevant context ...
{ "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": "MUL2648", "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_002493
train
audio
multi_turn
[ { "role": "user", "text": "is my name is lisa lisa coal. that's kow a l.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm also looking to book a train in the same place where i'm looking for information.", "turn_id": 2 }, { "role": "user", "text": "yes, and it shoul...
{ "chunk_text": "Chunk 1: is my name is lisa lisa coal. that's kow a l.\nChunk 2: yes, i'm also looking to book a train in the same place where i'm looking for information.\nChunk 3: yes, and it should go to stevenage.\nChunk 4: um i would like to travel and see so today is a survey i like to travel tomorrow and um i...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "is my name is lisa lisa coal. that's kow a l.", "role": "user", "streaming_reasoning": "The user mentions Is my name is lisa lisa coal. that's kow a l. It is not yet cle...
{ "answer": "Sure. I can provide the leaveat for the matching train option.", "reasoning": "Across the dialogue, the user is searching for information. Key context: is my name is lisa lisa coal; that's kow a l; yes, i'm also looking to book a train in the same place where i'm looking for information; yes, and it sh...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3732", "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_002494
train
audio
multi_turn
[ { "role": "user", "text": "are you. how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm all thank you. i need a base to stay cambridge.", "turn_id": 2 }, { "role": "user", "text": "uh, one that's not a hot on.", "turn_id": 3 }, { "role": "assistant"...
{ "chunk_text": "Chunk 1: are you. how are you.\nChunk 2: i'm all thank you. i need a base to stay cambridge.\nChunk 3: uh, one that's not a hot on.\nChunk 4: okay, i needed to have um to not charge me for parking.\nChunk 5: okay. does it offer free wifi.", "dialogue_text": "Chunk 1: are you. how are you.\nChunk 2:...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "are you. how are you.", "role": "user", "streaming_reasoning": "The user mentions Are you. how are you. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help with the hotel. Could you share the area, price?", "reasoning": "Across the dialogue, the user is talking about base to stay cambridge. Key context: how are you; i'm all thank you; i need a base to stay cambridge; uh, one that's not a hot on. The answer should focus on the latest user turn w...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2629", "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_000705
train
audio
multi_turn
[ { "role": "user", "text": "Human: True. It makes sense that when something cataclysmic occurs, something weaker is destroyed. How about the theory that there is only one electron in the universe. Surely that is not a serious th", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes...
{ "chunk_text": "Chunk 1: Human: True. It makes sense that when something cataclysmic occurs, something weaker is destroyed. How about the theory that there is only one electron in the universe. Surely that is not a serious theory.\nChunk 2: Assistant: Yes I don't know about that theory, or the theory that the univer...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: True. It makes sense that when something cataclysmic occurs, something weaker is destroyed. How about the theory that there is only one electron in the universe. Surely that ...
{ "answer": "I would definitely touch one of those Stars! Do you like Superman movies? Apparently he first made his appearance in the movies back in 1941", "reasoning": "Across the dialogue, the user is asking for help with human: true. Key context: Human: True; It makes sense that when something cataclysmic occurs...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_a8241ef5-654d-4c8d-8d63-0594d3ebb26f", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002495
train
audio
multi_turn
[ { "role": "user", "text": "okay, that's perfect. can i make a booking for 7 people. for this trip with the id 7 pr 7 9 3 8.", "turn_id": 1 }, { "role": "assistant", "text": "that will be 0 8, 4 0.", "turn_id": 2 }, { "role": "user", "text": "1 9 3 7.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: okay, that's perfect. can i make a booking for 7 people. for this trip with the id 7 pr 7 9 3 8.\nChunk 2: that will be 0 8, 4 0.\nChunk 3: 1 9 3 7.\nChunk 4: 7 2 5 9.\nChunk 5: 4, 7, 3, 7.\nChunk 6: alright great i'm also looking for a place to stay it should be located in the north and of ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, that's perfect. can i make a booking for 7 people. for this trip with the id 7 pr 7 9 3 8.", "role": "user", "streaming_reasoning": "The user mentions wanting to b...
{ "answer": "Sure. I can provide the phone, address, internet for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for place to stay it should be located in the north. Key context: okay, that's perfect; can i make a booking for 7 people; for this trip with the id 7 pr 7 9 3 8; t...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3151", "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_002496
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm planning a trip to cambridge. and i'm looking for places to go in town, perhaps some attraction like a museum.", "turn_id": 2 }, { "role": "user", "text": "um sure what's the entrance fee ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm planning a trip to cambridge. and i'm looking for places to go in town, perhaps some attraction like a museum.\nChunk 3: um sure what's the entrance fee for that.\nChunk 4: oh. okay. and what area of town is it in.\nChunk 5: oh that sounds good i'm also looking for a pla...
{ "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 find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for places to go in town. Key context: i'm planning a trip to cambridge; and i'm looking for places to go in town, perhaps some attraction like a museum; um sure what's the entran...
{ "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": "MUL3958", "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_002497
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.", "dialogue_text": "Chunk 1: hello. hello, am i said it's a customer sale.\nChunk 2: if john lang...
{ "num_checkpoints": 3, "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 with the train. Could you share the day, time?", "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 the ...
{ "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_multidialog_v02_000706
train
audio
multi_turn
[ { "role": "user", "text": "Human: Have you seen any good movies lately?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I actually haven't. I know Ryan Reynolds is in Deadpool and I like him. I just haven't gotten around to seeing it yet.", "turn_id": 2 }, { "role": ...
{ "chunk_text": "Chunk 1: Human: Have you seen any good movies lately?\nChunk 2: Assistant: I actually haven't. I know Ryan Reynolds is in Deadpool and I like him. I just haven't gotten around to seeing it yet.\nChunk 3: Human: Yeah - he was good in it. He's funny.", "dialogue_text": "Chunk 1: Human: Have you seen ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Have you seen any good movies lately?", "role": "user", "streaming_reasoning": "The user mentions Human: Have you seen any good movies lately?. It is not yet clea...
{ "answer": "He is funny. I liked him in that movie with Sandra Bullock.", "reasoning": "Across the dialogue, the user discusses \"Have you seen any good movies.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the d...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_00f2662b-0f83-4e00-b8e5-e731638f3690", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_002498
train
audio
multi_turn
[ { "role": "user", "text": "7 4 1.", "turn_id": 1 }, { "role": "assistant", "text": "8 9 9.", "turn_id": 2 }, { "role": "user", "text": "5, 7, 3, 6.", "turn_id": 3 }, { "role": "assistant", "text": "and then follows 9 3 0.", "turn_id": 4 }, { "role"...
{ "chunk_text": "Chunk 1: 7 4 1.\nChunk 2: 8 9 9.\nChunk 3: 5, 7, 3, 6.\nChunk 4: and then follows 9 3 0.\nChunk 5: yes, i still looking for a place to stay.\nChunk 6: yes, i think the hotel should be in the moderate price range, but i don't wanna pay for the parking.\nChunk 7: yes, thank you so much.\nChunk 8: yes. ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "7 4 1.", "role": "user", "streaming_reasoning": "The user mentions 7 4 1. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the hotel. Could you share the area, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: and then follows 9 3 0; yes, i still looking for a place to stay; yes, i think the hotel should be in the moderate price range, but i don't wanna p...
{ "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": "MUL0036", "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_002499
train
audio
multi_turn
[ { "role": "user", "text": "i prefer it should the trend should leave after across to 10 p m.", "turn_id": 1 }, { "role": "assistant", "text": "yes.", "turn_id": 2 }, { "role": "user", "text": "hmm, i suppose it's acceptable. so could you please tell me the. de- departure. um ...
{ "chunk_text": "Chunk 1: i prefer it should the trend should leave after across to 10 p m.\nChunk 2: yes.\nChunk 3: hmm, i suppose it's acceptable. so could you please tell me the. de- departure. um could you tell me the travel time of the trend.\nChunk 4: wow, that's good. that's okay.\nChunk 5: yes, i'm also looki...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i prefer it should the trend should leave after across to 10 p m.", "role": "user", "streaming_reasoning": "The user mentions talking about 10. It is not yet clear wheth...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for places to go in town. Key context: i prefer it should the trend should leave after across to 10 p m; hmm, i suppose it's acceptable; so could you please tell me the; de- depar...
{ "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": "MUL0123", "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_002500
train
audio
multi_turn
[ { "role": "user", "text": "hi, hello, good morning.", "turn_id": 1 }, { "role": "assistant", "text": "hi, how are you.", "turn_id": 2 }, { "role": "user", "text": "i'm thanks.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hi, hello, good morning.\nChunk 2: hi, how are you.\nChunk 3: i'm thanks.", "dialogue_text": "Chunk 1: hi, hello, good morning.\nChunk 2: hi, how are you.\nChunk 3: i'm thanks.", "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, good morning.", "role": "user", "streaming_reasoning": "The user mentions Hi, hello, good morning. It is not yet clear whether the user needs the full scope o...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user discusses \"hi, hello, good morning.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the use...
{ "category": "social_communication", "subcategory": "message_reply", "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": "MUL3702", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }