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_003997
train
audio
multi_turn
[ { "role": "user", "text": "the the, um. departure time, please.", "turn_id": 1 }, { "role": "assistant", "text": "okay. um could you also please assist me in looking for a place to stay, please.", "turn_id": 2 }, { "role": "user", "text": "yes um it should be in the cheap pri...
{ "chunk_text": "Chunk 1: the the, um. departure time, please.\nChunk 2: okay. um could you also please assist me in looking for a place to stay, please.\nChunk 3: yes um it should be in the cheap price range and include free parking um it also must be in the type of a guesthouse\nChunk 4: and also include free wi\nC...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "the the, um. departure time, please.", "role": "user", "streaming_reasoning": "The user mentions The the, um. departure time, please. It is not yet clear whether the use...
{ "answer": "Sure. I can provide the address, area, stars for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: the the, um; departure time, please; um could you also please assist me in looking for a place to stay, please; thank you, double your. ...
{ "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": "MUL2159", "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_001164
train
audio
multi_turn
[ { "role": "user", "text": "Human: I am doing well, thanks! Do you like football?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I usually watch NFL right around playoff time. Do you like football?", "turn_id": 2 }, { "role": "user", "text": "Human: I love it! di...
{ "chunk_text": "Chunk 1: Human: I am doing well, thanks! Do you like football?\nChunk 2: Assistant: I usually watch NFL right around playoff time. Do you like football?\nChunk 3: Human: I love it! did you know iowa's locker room for their visitors is pink?", "dialogue_text": "Chunk 1: Human: I am doing well, thank...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I am doing well, thanks! Do you like football?", "role": "user", "streaming_reasoning": "The user mentions Human: I am doing well, thanks! Do you like football?. ...
{ "answer": "Iowa is trying some sort of mind game. I don't think it works well or other teams would imitate. How has Iowa done at home?", "reasoning": "Across the dialogue, the user discusses \"I am doing well, thanks! Do you like.\" over 3 turns. The answer should respond to the latest user turn naturally, mainta...
{ "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_bad4a692-87cc-4dbb-8315-6254332c2262", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003998
train
audio
multi_turn
[ { "role": "user", "text": "okay, thank you very much.", "turn_id": 1 }, { "role": "assistant", "text": "oh, what's a pity, but it's it's quite acceptable for me. so may.", "turn_id": 2 }, { "role": "user", "text": "yeah. um, i prefer the festival.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: okay, thank you very much.\nChunk 2: oh, what's a pity, but it's it's quite acceptable for me. so may.\nChunk 3: yeah. um, i prefer the festival.\nChunk 4: okay. and what's the next.\nChunk 5: yes, i prefer to take one and could you please make a renovation for us.\nChunk 6: well, i need a r...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, thank you very much.", "role": "user", "streaming_reasoning": "The user mentions Okay, thank you very much. It is not yet clear whether the user needs the full sco...
{ "answer": "I can help book that. Could you provide the price?", "reasoning": "Across the dialogue, the user is wanting to book room for totally sweet. Key context: okay, thank you very much; oh, what's a pity, but it's it's quite acceptable for me; um, i prefer the festival; and what's the next. The answer should...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1136", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003999
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm good. how are you.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train that goes to stevens.", "turn_id": 3 }, { "role": "assistant", "text": "um departing...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm good. how are you.\nChunk 3: i'm looking for a train that goes to stevens.\nChunk 4: um departing from cambridge.\nChunk 5: um, uh, let's i want to live on the day before sunday to sunday, sorry.\nChunk 6: if it can arrive. at stevens, an hour after 2.\nChunk 7: okay, th...
{ "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 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 that goes to stevens. Key context: how are you; i'm looking for a train that goes to stevens; um departing from cambridge; um, uh, let's i w...
{ "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": "SNG0355", "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_001165
train
audio
multi_turn
[ { "role": "user", "text": "Human: For sure. She is also a business woman and co-owns Miami Dolphins", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Thats good to know. I would say that is a pretty sound investment.", "turn_id": 2 }, { "role": "user", "text": "Hum...
{ "chunk_text": "Chunk 1: Human: For sure. She is also a business woman and co-owns Miami Dolphins\nChunk 2: Assistant: Thats good to know. I would say that is a pretty sound investment.\nChunk 3: Human: I think so too. And she speaks 3 languages fluently, as does her sister Venus", "dialogue_text": "Chunk 1: Human...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: For sure. She is also a business woman and co-owns Miami Dolphins", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Miami Dolphins....
{ "answer": "Wonder how she learned all those languages. It isnt really that common for somebody to know more than two languages.", "reasoning": "Across the dialogue, the user discusses \"For sure. She is also a business woman and co-owns Miami.\" over 3 turns. The answer should respond to the latest user turn natu...
{ "category": "finance_consumer", "subcategory": "budget_planning", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_efea5741-2fa3-406d-a49f-cc8178fd878d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004000
train
audio
multi_turn
[ { "role": "user", "text": "hello, i'm looking for train service, please.", "turn_id": 1 }, { "role": "assistant", "text": "departing from a eastern midland area and heading towards university town.", "turn_id": 2 }, { "role": "user", "text": "okay, i'm planning to leave on th...
{ "chunk_text": "Chunk 1: hello, i'm looking for train service, please.\nChunk 2: departing from a eastern midland area and heading towards university town.\nChunk 3: okay, i'm planning to leave on thursday. and, uh, arriving by 3 45 pm.\nChunk 4: sure, thanks.\nChunk 5: okay, great. um. could you kindly help me make...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, i'm looking for train service, please.", "role": "user", "streaming_reasoning": "The user mentions Hello, i'm looking for train service, please. It is not yet cle...
{ "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 service. Key context: hello, i'm looking for train service, please; departing from a eastern midland area and heading towards university tow...
{ "category": "education", "subcategory": "course_planning", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3269", "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_004001
train
audio
multi_turn
[ { "role": "user", "text": "are you speaking to surely autumn.", "turn_id": 1 }, { "role": "assistant", "text": "i am looking for a place to stay.", "turn_id": 2 }, { "role": "user", "text": "ambassador cambridge.", "turn_id": 3 }, { "role": "assistant", "text"...
{ "chunk_text": "Chunk 1: are you speaking to surely autumn.\nChunk 2: i am looking for a place to stay.\nChunk 3: ambassador cambridge.\nChunk 4: a hotel that has four staff. advance just.\nChunk 5: it might be expensive.\nChunk 6: um in the north. fight.\nChunk 7: yes.\nChunk 8: then i will settle for the moderate ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "are you speaking to surely autumn.", "role": "user", "streaming_reasoning": "The user mentions Are you speaking to surely autumn. It is not yet clear whether the user ne...
{ "answer": "I can help with the hotel. Could you share the hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: are you speaking to surely autumn; i am looking for a place to stay; ambassador cambridge; a hotel that has four staff. The answer should focus on the la...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "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_multidialog_v02_001166
train
audio
multi_turn
[ { "role": "user", "text": "Human: I didn't know that. What did he do for him?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Well Chadwick was accepted to a prestigious summer theater program at Oxford University but could not afford it, so Washington stepped in. Chadwick thank...
{ "chunk_text": "Chunk 1: Human: I didn't know that. What did he do for him?\nChunk 2: Assistant: Well Chadwick was accepted to a prestigious summer theater program at Oxford University but could not afford it, so Washington stepped in. Chadwick thanked him 20 years later at the premier of black panther.\nChunk 3: Hu...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I didn't know that. What did he do for him?", "role": "user", "streaming_reasoning": "The user mentions Human: I didn't know that. What did he do for him?. It is ...
{ "answer": "Can you imagine Jack black as the Green lantern?", "reasoning": "Across the dialogue, the user is asking for help with human: i didn't know that. Key context: Human: I didn't know that; What did he do for him; Assistant: Well Chadwick was accepted to a prestigious summer theater program at Oxford Unive...
{ "category": "education", "subcategory": "course_planning", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_3ada71c7-00b1-4079-9e68-947de5ef338e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004002
train
audio
multi_turn
[ { "role": "user", "text": "yes, sure. i'd like to book it for. 8 people from this saturday to let me see. okay. sunday, monday, tuesday to wednesday.", "turn_id": 1 }, { "role": "assistant", "text": "oh, yes, it is.", "turn_id": 2 }, { "role": "user", "text": "sure, my name i...
{ "chunk_text": "Chunk 1: yes, sure. i'd like to book it for. 8 people from this saturday to let me see. okay. sunday, monday, tuesday to wednesday.\nChunk 2: oh, yes, it is.\nChunk 3: sure, my name is fatima watson.\nChunk 4: yeah, sure, five months. sounds like f a t i m a. waterfront. sounds like w a t s o n.\nChu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, sure. i'd like to book it for. 8 people from this saturday to let me see. okay. sunday, monday, tuesday to wednesday.", "role": "user", "streaming_reasoning": "The ...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book it for. Key context: i'd like to book it for; 8 people from this saturday to let me see; sunday, monday, tuesday to wednesday; oh, yes, it is. The answer should focus on...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1933", "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_004003
train
audio
multi_turn
[ { "role": "user", "text": "it should be ebay.", "turn_id": 1 }, { "role": "assistant", "text": "f i t z g r.", "turn_id": 2 }, { "role": "user", "text": "a l d.", "turn_id": 3 }, { "role": "assistant", "text": "shi.", "turn_id": 4 }, { "role": "use...
{ "chunk_text": "Chunk 1: it should be ebay.\nChunk 2: f i t z g r.\nChunk 3: a l d.\nChunk 4: shi.\nChunk 5: thank you so much.\nChunk 6: i'm also looking for a particular attraction.\nChunk 7: xue is it's called old skills.\nChunk 8: may i know the area of the the attraction.", "dialogue_text": "Chunk 1: it shoul...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "it should be ebay.", "role": "user", "streaming_reasoning": "The user mentions It should be ebay. It is not yet clear whether the user needs the full scope of the user's...
{ "answer": "Sure. I can provide the area for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for particular attraction. Key context: it should be ebay; f i t z g r; thank you so much; i'm also looking for a particular attraction. The answer should focus on the latest user...
{ "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": "MUL0471", "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_001167
train
audio
multi_turn
[ { "role": "user", "text": "Human: I have to agree, I don't understand what is exciting about it. But most of the rest of the world clearly loves it. I wonder what city the 2022 world cup is going to be in that doesn't yet exist", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Wit...
{ "chunk_text": "Chunk 1: Human: I have to agree, I don't understand what is exciting about it. But most of the rest of the world clearly loves it. I wonder what city the 2022 world cup is going to be in that doesn't yet exist?\nChunk 2: Assistant: Without looking it up, my guess is that Qatar is building a city to h...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I have to agree, I don't understand what is exciting about it. But most of the rest of the world clearly loves it. I wonder what city the 2022 world cup is going to be in tha...
{ "answer": "I did see it and liked it. It was during the period that my granddaughter imagined Wonder Woman everywhere saving people. I liked the fact that in 2017 the 3 highest grossing domestic films were female led.", "reasoning": "Across the dialogue, the user is asking about human: i have to agree, i don't un...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "fact_lookup" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_71e1bfa5-cee8-4a83-aaa3-5b7cb6ca5880", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_001168
train
audio
multi_turn
[ { "role": "user", "text": "Human: I know, what a reach. did you know that panda researchers wear panda costumes?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: What? Well Johnny Depp brings his Jack Sparrow costume with him when he travels. That way he can visit sick kids in th...
{ "chunk_text": "Chunk 1: Human: I know, what a reach. did you know that panda researchers wear panda costumes?\nChunk 2: Assistant: What? Well Johnny Depp brings his Jack Sparrow costume with him when he travels. That way he can visit sick kids in the hospital and surprise them.\nChunk 3: Human: That is so nice sinc...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I know, what a reach. did you know that panda researchers wear panda costumes?", "role": "user", "streaming_reasoning": "The user mentions searching for Human. It...
{ "answer": "Wow. I didn't know that. I love costumes from movies.", "reasoning": "Across the dialogue, the user is searching for human: i know, what a reach. Key context: Human: I know, what a reach; did you know that panda researchers wear panda costumes; Assistant: What; Well Johnny Depp brings his Jack Sparrow ...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_9221f3d7-601c-42b9-bce3-1d8820ff1ff1", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004004
train
audio
multi_turn
[ { "role": "user", "text": "and on wednesday.", "turn_id": 1 }, { "role": "assistant", "text": "and arrive at half this ache.", "turn_id": 2 }, { "role": "user", "text": "uh, in the morning.", "turn_id": 3 }, { "role": "assistant", "text": "yes.", "turn_id"...
{ "chunk_text": "Chunk 1: and on wednesday.\nChunk 2: and arrive at half this ache.\nChunk 3: uh, in the morning.\nChunk 4: yes.\nChunk 5: yes.\nChunk 6: and three of us.\nChunk 7: id number 4 1.\nChunk 8: 0 5.", "dialogue_text": "Chunk 1: and on wednesday.\nChunk 2: and arrive at half this ache.\nChunk 3: uh, in t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and on wednesday.", "role": "user", "streaming_reasoning": "The user mentions And on wednesday. It is not yet clear whether the user needs the full scope of the user's r...
{ "answer": "I can help with the train. Could you share the departure, destination?", "reasoning": "Across the dialogue, the user is talking about and on wednesday. Key context: and on wednesday; and arrive at half this ache; uh, in the morning; and three of us. The answer should focus on the latest user turn while...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "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_spokenwoz_v02_004005
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is andrew.", "turn_id": 1 }, { "role": "assistant", "text": "i am annoyed i'm buying a trip to cambridge and i'm looking for place to visit to dental.", "turn_id": 2 }, { "role": "user", "text": "uh, okay, says something with architects ...
{ "chunk_text": "Chunk 1: hi, my name is andrew.\nChunk 2: i am annoyed i'm buying a trip to cambridge and i'm looking for place to visit to dental.\nChunk 3: uh, okay, says something with architects or something of the similar particle.\nChunk 4: preferably on the western side is also.\nChunk 5: yes, i call it.\nChu...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is andrew.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is andrew. It is not yet clear whether the user needs the full scope of th...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for place to visit to dental. Key context: hi, my name is andrew; i am annoyed i'm buying a trip to cambridge and i'm looking for place to visit to dental; uh, okay, says somethin...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "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": "MUL1407", "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_001169
train
audio
multi_turn
[ { "role": "user", "text": "Human: Wow! What are the odds of that. What a neat story!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Can you imagine Jack black as the Green lantern?", "turn_id": 2 }, { "role": "user", "text": "Human: I kind of have a feeling I wo...
{ "chunk_text": "Chunk 1: Human: Wow! What are the odds of that. What a neat story!\nChunk 2: Assistant: Can you imagine Jack black as the Green lantern?\nChunk 3: Human: I kind of have a feeling I would have liked that movie more.", "dialogue_text": "Chunk 1: Human: Wow! What are the odds of that. What a neat stor...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Wow! What are the odds of that. What a neat story!", "role": "user", "streaming_reasoning": "The user mentions Human: Wow! What are the odds of that. What a neat ...
{ "answer": "I can't see him in that role but i guess if it was going to be a comedy it would have been very good, i like Black.", "reasoning": "Across the dialogue, the user discusses \"Wow! What are the odds of that. What a neat.\" over 3 turns. The answer should respond to the latest user turn naturally, maintai...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_3ada71c7-00b1-4079-9e68-947de5ef338e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004006
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "um yes, i am looking for some information in cambridge. were you able to help me.", "turn_id": 2 }, { "role": "user", "text": "so i'm looking for a particular place. the name is called jesus g...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: um yes, i am looking for some information in cambridge. were you able to help me.\nChunk 3: so i'm looking for a particular place. the name is called jesus green outdoor pool.\nChunk 4: yes, jesus j e s u s jesus. jesus green, g r e and green outdoor pool.\nChunk 5: mmhmm.\n...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "Sure. I can provide the area for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: um yes, i am looking for some information in cambridge; were you able to help me; so i'm looking for a particular place; the name is cal...
{ "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": "MUL1880", "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_004007
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for more information in cambridge.", "turn_id": 2 }, { "role": "user", "text": "mm. well, i'm looking for a trend.", "turn_id": 3 }, { "role": "assistant", "te...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for more information in cambridge.\nChunk 3: mm. well, i'm looking for a trend.\nChunk 4: the trend should live on sunday.\nChunk 5: um and should depart from kingston.\nChunk 6: um i'm going to cambridge.", "dialogue_text": "Chunk 1: hello.\nChunk 2: yes,...
{ "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 train. Could you share the time?", "reasoning": "Across the dialogue, the user is searching for more information in cambridge. Key context: yes, i'm looking for more information in cambridge; well, i'm looking for a trend; the trend should live on sunday; um and should depart from k...
{ "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": "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_004008
train
audio
multi_turn
[ { "role": "user", "text": "uh, so what. uh, 6 45 p.", "turn_id": 1 }, { "role": "assistant", "text": "uh, that's great. thank.", "turn_id": 2 }, { "role": "user", "text": "ah yes, of course, my name is dorothy.", "turn_id": 3 }, { "role": "assistant", "text": ...
{ "chunk_text": "Chunk 1: uh, so what. uh, 6 45 p.\nChunk 2: uh, that's great. thank.\nChunk 3: ah yes, of course, my name is dorothy.\nChunk 4: uh, sure as i'm i t h.\nChunk 5: uh, yes, i'm happy to and my email is d s with capital letters.\nChunk 6: uh, i'm a t h.\nChunk 7: w y 7 v.\nChunk 8: up. hotmail dot com an...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, so what. uh, 6 45 p.", "role": "user", "streaming_reasoning": "The user mentions Uh, so what. uh, 6 45 p. It is not yet clear whether the user needs the full scope o...
{ "answer": "I can help with the restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is talking about uh, so what. Key context: uh, so what; uh, that's great; ah yes, of course, my name is dorothy; uh, sure as i'm i t h. The answer should focus on the latest user turn wh...
{ "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": "MUL0233", "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_004009
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a place to go in town.", "turn_id": 2 }, { "role": "user", "text": "yes, i think, ah, the type of college will be great.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a place to go in town.\nChunk 3: yes, i think, ah, the type of college will be great.", "dialogue_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a place to go in town.\nChunk 3: yes, i think, ah, the type of college will be great.", "instruct...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: yes, i'm looking for a place to go in town; yes, i think, ah, the type of college will be great. The answer should focus on the latest user turn whi...
{ "category": "education", "subcategory": "course_planning", "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": "MUL0486", "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_004010
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "um okay, and you.", "turn_id": 2 }, { "role": "user", "text": "um i'm looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "the train should leave. no, ...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: um okay, and you.\nChunk 3: um i'm looking for a train.\nChunk 4: the train should leave. no, wait. going to cambridge.\nChunk 5: on monday.", "dialogue_text": "Chunk 1: hello. hello.\nChunk 2: um okay, and you.\nChunk 3: um i'm looking for a train.\nChunk 4: the tr...
{ "num_checkpoints": 5, "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 train. Could you share the time?", "reasoning": "Across the dialogue, the user is searching for train. Key context: um okay, and you; um i'm looking for a train; the train should leave; going to cambridge. The answer should focus on the latest user turn while incorporating relevant ...
{ "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": "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_004011
train
audio
multi_turn
[ { "role": "user", "text": "thank you so much. i'm also looking for a place to stay.", "turn_id": 1 }, { "role": "assistant", "text": "moderate, please.", "turn_id": 2 }, { "role": "user", "text": "yes, i would like to book for 8 people and four nights.", "turn_id": 3 },...
{ "chunk_text": "Chunk 1: thank you so much. i'm also looking for a place to stay.\nChunk 2: moderate, please.\nChunk 3: yes, i would like to book for 8 people and four nights.\nChunk 4: wednesday.\nChunk 5: how about three knives.\nChunk 6: my name is elton singleton. elt o n is the first name.\nChunk 7: yes. my ema...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "thank you so much. i'm also looking for a place to stay.", "role": "user", "streaming_reasoning": "The user mentions Thank you so much. i'm also looking for a place to s...
{ "answer": "I can help book that. Could you provide the area, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: thank you so much; i'm also looking for a place to stay; moderate, please; yes, i would like to book for 8 people and four nights. The answer should f...
{ "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": "MUL3078", "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_004012
train
audio
multi_turn
[ { "role": "user", "text": "so i'm looking for a train that should depart from cambridge, going to bishop stratford.", "turn_id": 1 }, { "role": "assistant", "text": "okay so the train that i'm interested in should um depart from cambridge on a tuesday and should arrive into bishops stortford...
{ "chunk_text": "Chunk 1: so i'm looking for a train that should depart from cambridge, going to bishop stratford.\nChunk 2: okay so the train that i'm interested in should um depart from cambridge on a tuesday and should arrive into bishops stortford right now it's\nChunk 3: 7 45 a m so by two hours from now\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "so i'm looking for a train that should depart from cambridge, going to bishop stratford.", "role": "user", "streaming_reasoning": "The user mentions searching for stratf...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for train that should depart from cambridge. Key context: so i'm looking for a train that should depart from cambridge, going to bishop stratford; okay so the train that i'...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "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": "MUL2185", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_001170
train
audio
multi_turn
[ { "role": "user", "text": "Human: did you know that a deaf quarterback came up with the huddle? I guess it would block the other team from seeing his hand signals", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That's an interesting fact. Do you enjoy football and the nfl?", ...
{ "chunk_text": "Chunk 1: Human: did you know that a deaf quarterback came up with the huddle? I guess it would block the other team from seeing his hand signals\nChunk 2: Assistant: That's an interesting fact. Do you enjoy football and the nfl?\nChunk 3: Human: Football is ok, I don't really like the NFL but I toler...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: did you know that a deaf quarterback came up with the huddle? I guess it would block the other team from seeing his hand signals", "role": "user", "streaming_reas...
{ "answer": "Well the NFL has done a decent job as it is now recognized as among the 4 major sport leagues in North America.", "reasoning": "Across the dialogue, the user is asking for help with human: did you know that a deaf quarterback came up with the huddle. Key context: Human: did you know that a deaf quarter...
{ "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_1caa0f05-2b14-46e0-bdf1-dcfd72d48856", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004013
train
audio
multi_turn
[ { "role": "user", "text": "h ua a.", "turn_id": 1 }, { "role": "assistant", "text": "ah sorry. hate you, eh.", "turn_id": 2 }, { "role": "user", "text": "um ya and like. my last name is johns, which is called j o h.", "turn_id": 3 }, { "role": "assistant", "te...
{ "chunk_text": "Chunk 1: h ua a.\nChunk 2: ah sorry. hate you, eh.\nChunk 3: um ya and like. my last name is johns, which is called j o h.\nChunk 4: and yes.\nChunk 5: um, okay. how about for one night.\nChunk 6: uh, yeah, that would be great. i'll give you my email address.\nChunk 7: um it is jj o h.\nChunk 8: n s ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "h ua a.", "role": "user", "streaming_reasoning": "The user mentions H ua a. 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 hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is talking about j o h. Key context: hate you, eh; um ya and like; my last name is johns, which is called j o h; how about for one night. The answer should focus on the latest user turn...
{ "category": "work_productivity", "subcategory": "meeting_summary", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3237", "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_004014
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm planning a trip to cambridge and looking for a place to dine i'd like a restaurant in the center of town and something serving", "turn_id": 2 }, { "role": "user", "text": "modern european ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm planning a trip to cambridge and looking for a place to dine i'd like a restaurant in the center of town and something serving\nChunk 3: modern european food", "dialogue_text": "Chunk 1: hello.\nChunk 2: i'm planning a trip to cambridge and looking for a place to dine ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the restaurant. Could you share the price?", "reasoning": "Across the dialogue, the user is searching for place to dine i'd like a restaurant in the center of town. Key context: i'm planning a trip to cambridge and looking for a place to dine i'd like a restaurant in the center of town ...
{ "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": "MUL3376", "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_004015
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm traveling to cambridge and looking first for a train.", "turn_id": 2 }, { "role": "user", "text": "going to cambridge leaving around let's see around 6 45 pm and i need to be in cambridge ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm traveling to cambridge and looking first for a train.\nChunk 3: going to cambridge leaving around let's see around 6 45 pm and i need to be in cambridge the day before my meeting which is\nChunk 4: on sunday october 15 and leaving from bishop stortford\nChunk 5: yes, tha...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is wanting to book to be in cambridge the day before my meeting which is on sunday october 15. Key context: i'm traveling to cambridge and looking first for a trai...
{ "category": "work_productivity", "subcategory": "meeting_summary", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3407", "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_004016
train
audio
multi_turn
[ { "role": "user", "text": "and hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm great. thanks. i'm looking for a place to stay in cambridge.", "turn_id": 2 }, { "role": "user", "text": "the hotel should be in the milton country park area and should be...
{ "chunk_text": "Chunk 1: and hello, how are you.\nChunk 2: i'm great. thanks. i'm looking for a place to stay in cambridge.\nChunk 3: the hotel should be in the milton country park area and should be in the type of a guesthouse with free wifi.\nChunk 4: okay.\nChunk 5: the acorn guesthouse from.\nChunk 6: yes, peace...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions And hello, how are you. It is not yet clear whether the user needs the full scope of ...
{ "answer": "I can help with the hotel. Could you share the area, price?", "reasoning": "Across the dialogue, the user is searching for place to stay in cambridge. Key context: and hello, how are you; i'm looking for a place to stay in cambridge; the hotel should be in the milton country park area and should be in ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2805", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004017
train
audio
multi_turn
[ { "role": "user", "text": "yes, and i should depart from london liverpool street and go to cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "okay, thank you very much.", "turn_id": 2 }, { "role": "user", "text": "yes, that's sure that's okay. and please make reserv...
{ "chunk_text": "Chunk 1: yes, and i should depart from london liverpool street and go to cambridge.\nChunk 2: okay, thank you very much.\nChunk 3: yes, that's sure that's okay. and please make reservation for the same group of people.\nChunk 4: mm. yes, and my id number should be. 5 8 6 2.\nChunk 5: 2 2, 4 2.\nChunk...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, and i should depart from london liverpool street and go to cambridge.", "role": "user", "streaming_reasoning": "The user mentions Yes, and i should depart from lond...
{ "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 talking about to receive the confirm orders via email so i would like. Key context: yes, and i should depart from london liverpool street and go to cambridge; o...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1133", "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_001171
train
audio
multi_turn
[ { "role": "user", "text": "Human: Ya and they have amazing players like brady. Surprised he is still playing, but his performance is still solid", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I agree, he is 40 years old but still one of the best QB on the league, wonder how muc...
{ "chunk_text": "Chunk 1: Human: Ya and they have amazing players like brady. Surprised he is still playing, but his performance is still solid\nChunk 2: Assistant: I agree, he is 40 years old but still one of the best QB on the league, wonder how much money he makes, must be a lot\nChunk 3: Human: I hear his wife st...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Ya and they have amazing players like brady. Surprised he is still playing, but his performance is still solid", "role": "user", "streaming_reasoning": "The user ...
{ "answer": "She is a famous model or was a famous model to think engineers actually end up winning more than pro football players", "reasoning": "Across the dialogue, the user discusses \"Ya and they have amazing players like brady. Surprised he.\" over 3 turns. The answer should respond to the latest user turn na...
{ "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_12ad4ff3-085c-4337-8fb7-c0d6a2174c10", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004018
train
audio
multi_turn
[ { "role": "user", "text": "uh, yes, i will. i plan to make a booking, please help me.", "turn_id": 1 }, { "role": "assistant", "text": "okay, i will choose this one.", "turn_id": 2 }, { "role": "user", "text": "yes, i want to booking for white people.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: uh, yes, i will. i plan to make a booking, please help me.\nChunk 2: okay, i will choose this one.\nChunk 3: yes, i want to booking for white people.\nChunk 4: ok, thank you.\nChunk 5: yes, it's 0 1 8 1.\nChunk 6: double 9 3 7.\nChunk 7: 1 2 9 2.\nChunk 8: 3 8 2 8 that's all.", "dialogue_t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, yes, i will. i plan to make a booking, please help me.", "role": "user", "streaming_reasoning": "The user mentions Uh, yes, i will. i plan to make a booking, please ...
{ "answer": "I can help book that. Could you provide the departure, destination, day?", "reasoning": "Across the dialogue, the user is wanting to book to booking for white people. Key context: uh, yes, i will; i plan to make a booking, please help me; okay, i will choose this one; yes, i want to booking for white p...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3932", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004019
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.\nChunk 6:...
{ "num_checkpoints": 7, "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": "Sure. I can provide the address for the matching restaurant option.", "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 i...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0972", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004020
train
audio
multi_turn
[ { "role": "user", "text": "the train should go to cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "and he should leave on thursday.", "turn_id": 2 }, { "role": "user", "text": "and it should depart. from, uh, my sister.", "turn_id": 3 }, { "role": "ass...
{ "chunk_text": "Chunk 1: the train should go to cambridge.\nChunk 2: and he should leave on thursday.\nChunk 3: and it should depart. from, uh, my sister.\nChunk 4: okay, that's great. so i want to book tickets for eight people.\nChunk 5: sure, my id number is 2 2, 8, double 9.\nChunk 6: 0 double 8 1.\nChunk 7: 7 5 ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "the train should go to cambridge.", "role": "user", "streaming_reasoning": "The user mentions The train should go to cambridge. It is not yet clear whether the user need...
{ "answer": "I can help book that. Could you provide the time?", "reasoning": "Across the dialogue, the user is wanting to book tickets for eight people. Key context: the train should go to cambridge; and he should leave on thursday; and it should depart; from, uh, my sister. The answer should focus on the latest u...
{ "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": "MUL1708", "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_004021
train
audio
multi_turn
[ { "role": "user", "text": "oh. okay, thank you so much.", "turn_id": 1 }, { "role": "assistant", "text": "that's right.", "turn_id": 2 }, { "role": "user", "text": "share my telephone number should be. size 9 sets.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: oh. okay, thank you so much.\nChunk 2: that's right.\nChunk 3: share my telephone number should be. size 9 sets.\nChunk 4: 1, 8, 7.\nChunk 5: 4, 6, 7.\nChunk 6: 9.\nChunk 7: okay.\nChunk 8: thank you so much.", "dialogue_text": "Chunk 1: oh. okay, thank you so much.\nChunk 2: that's right....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "oh. okay, thank you so much.", "role": "user", "streaming_reasoning": "The user mentions Oh. okay, thank you so much. It is not yet clear whether the user needs the full...
{ "answer": "I can help with the taxi. Could you share the departure, destination, time?", "reasoning": "Across the dialogue, the user is talking about okay, thank you so much. Key context: okay, thank you so much; that's right; share my telephone number should be; size 9 sets. The answer should focus on the latest...
{ "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": "SNG0095", "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_000144
train
audio
multi_turn
[ { "role": "user", "text": "Do I need sunscreen if it's cloudy?", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: Do I need sunscreen if it's cloudy?", "dialogue_text": "Chunk 1: Do I need sunscreen if it's cloudy?", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chunks.", "length_bucket": "short", "num_turns": 1, "total_tran...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Do I need sunscreen if it's cloudy?", "role": "user", "streaming_reasoning": "The user mentions Do I need sunscreen if it's cloudy?. It is not yet clear whether the user...
{ "answer": "Absolutely, UV rays can penetrate through clouds, and the sound of the waves indicates you're out in the open, making sunscreen necessary.", "reasoning": "Across the dialogue, the user is talking about sunscreen if it's cloudy. Key context: Do I need sunscreen if it's cloudy. The answer should focus on...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "easy", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SD-Eval", "dialogue_id": "103_4", "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_004022
train
audio
multi_turn
[ { "role": "user", "text": "yes, ma'am.", "turn_id": 1 }, { "role": "assistant", "text": "yes, the train should go to cambridge and should leave after 15 0 0 0.", "turn_id": 2 }, { "role": "user", "text": "1550. that that's okay with me, man.", "turn_id": 3 }, { "r...
{ "chunk_text": "Chunk 1: yes, ma'am.\nChunk 2: yes, the train should go to cambridge and should leave after 15 0 0 0.\nChunk 3: 1550. that that's okay with me, man.\nChunk 4: yes, i want to get both of the same good things.\nChunk 5: yeah, it will 2 0, 6, 1.\nChunk 6: 2 7 double 5.\nChunk 7: 1 0 8 4.\nChunk 8: 7, 6,...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, ma'am.", "role": "user", "streaming_reasoning": "The user mentions Yes, ma'am. It is not yet clear whether the user needs the full scope of the user's request. The ...
{ "answer": "I can help with the train. Could you share the departure, day, time?", "reasoning": "Across the dialogue, the user is asking for recommendations about to get both of the same good things. Key context: yes, the train should go to cambridge and should leave after 15 0 0 0; that that's okay with me, man; ...
{ "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": "MUL1101", "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_001172
train
audio
multi_turn
[ { "role": "user", "text": "Human: I watch it sometimes. They banned the dunk for awhile because Kareem.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: What did Kareem do? Did he play for Kansas where james naissmith was a losing coach?", "turn_id": 2 }, { "role": "u...
{ "chunk_text": "Chunk 1: Human: I watch it sometimes. They banned the dunk for awhile because Kareem.\nChunk 2: Assistant: What did Kareem do? Did he play for Kansas where james naissmith was a losing coach?\nChunk 3: Human: He was just a really good player that could slam dunk.", "dialogue_text": "Chunk 1: Human:...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I watch it sometimes. They banned the dunk for awhile because Kareem.", "role": "user", "streaming_reasoning": "The user mentions talking about Human, They, Karee...
{ "answer": "He should have gone into coaching. Some of the highest state paid employees are coaches.", "reasoning": "Across the dialogue, the user discusses \"I watch it sometimes. They banned the dunk for awhile.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversa...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_d9abed6c-46d6-401c-a307-2e0f699868a2", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004023
train
audio
multi_turn
[ { "role": "user", "text": "7 2 5 0", "turn_id": 1 }, { "role": "assistant", "text": "and 1 9 3 4.", "turn_id": 2 }, { "role": "user", "text": "yes. um, and 4 8 9 2.", "turn_id": 3 }, { "role": "assistant", "text": "and i live and the last four should be 9 4 8 ...
{ "chunk_text": "Chunk 1: 7 2 5 0\nChunk 2: and 1 9 3 4.\nChunk 3: yes. um, and 4 8 9 2.\nChunk 4: and i live and the last four should be 9 4 8 8.\nChunk 5: okay, thank you very much.\nChunk 6: um yes. i am also looking for a particular hotel.\nChunk 7: yes. um, the name is called gong v hotel.\nChunk 8: yes, it shou...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "7 2 5 0", "role": "user", "streaming_reasoning": "The user mentions 7 2 5 0. It is not yet clear whether the user needs the full scope of the user's request. The assista...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for particular hotel. Key context: 7 2 5 0 and 1 9 3 4; um, and 4 8 9 2; and i live and the last four should be 9 4 8 8; okay, thank you very much. The answer should focus ...
{ "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": "MUL1840", "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_004024
train
audio
multi_turn
[ { "role": "user", "text": "sure thing. it's a 1, 3, 4, 6.", "turn_id": 1 }, { "role": "assistant", "text": "yes. and then 0, 3, 2, 5.", "turn_id": 2 }, { "role": "user", "text": "yes. and then lastly, 4, 8.", "turn_id": 3 }, { "role": "assistant", "text": "yes...
{ "chunk_text": "Chunk 1: sure thing. it's a 1, 3, 4, 6.\nChunk 2: yes. and then 0, 3, 2, 5.\nChunk 3: yes. and then lastly, 4, 8.\nChunk 4: yes, that is correct.\nChunk 5: um yes, um can you please give me the carton.\nChunk 6: okay. thank you very much.\nChunk 7: tesla, okay. thank you very much.\nChunk 8: no, than...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "sure thing. it's a 1, 3, 4, 6.", "role": "user", "streaming_reasoning": "The user mentions Sure thing. it's a 1, 3, 4, 6. It is not yet clear whether the user needs the ...
{ "answer": "Sure. I can provide the car for the matching taxi option.", "reasoning": "Across the dialogue, the user is talking about it's a 1, 3, 4, 6. Key context: it's a 1, 3, 4, 6; and then 0, 3, 2, 5; and then lastly, 4, 8; yes, that is correct. The answer should focus on the latest user turn while incorporati...
{ "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": "SNG1714", "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_004025
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i was looking for a train, please.", "turn_id": 2 }, { "role": "user", "text": "yes, i'm departing. well, i'm going to be visiting eli cathedral and i need to go to cambridge.", "turn_id":...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i was looking for a train, please.\nChunk 3: yes, i'm departing. well, i'm going to be visiting eli cathedral and i need to go to cambridge.\nChunk 4: yeah, so next wednesday leaving after 9 15 pm.\nChunk 5: i just need price first.\nChunk 6: thank you. and did you give me t...
{ "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 ticket, arriveby, travel_time for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train. Key context: i was looking for a train, please; yes, i'm departing; well, i'm going to be visiting eli cathedral and i need to go to cambridge; yeah...
{ "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": "SNG1466", "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_004026
train
audio
multi_turn
[ { "role": "user", "text": "i'd like to book a taxi to commute between the two places.", "turn_id": 1 }, { "role": "assistant", "text": "it should arrive the restaurant by 1215, please.", "turn_id": 2 }, { "role": "user", "text": "yes, my phone number is 5 3 9.", "turn_id"...
{ "chunk_text": "Chunk 1: i'd like to book a taxi to commute between the two places.\nChunk 2: it should arrive the restaurant by 1215, please.\nChunk 3: yes, my phone number is 5 3 9.\nChunk 4: 3, 1, 1.\nChunk 5: 1 9 4 5.\nChunk 6: can i get the car type, please.\nChunk 7: perfect, thank you so much.\nChunk 8: that ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'd like to book a taxi to commute between the two places.", "role": "user", "streaming_reasoning": "The user mentions I'd like to book a taxi to commute between the two...
{ "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 commute between the two places. Key context: i'd like to book a taxi to commute between the two places; it should arrive the restaurant by 1215, please; yes, my phone nu...
{ "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": "MUL3091", "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_001173
train
audio
multi_turn
[ { "role": "user", "text": "Human: I thought it was because the average career is 2 yeras vs an engineers beings 30 years. Do you have a favorite team?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah that could be it, I do have a favorite team I love the Patriots I became a ...
{ "chunk_text": "Chunk 1: Human: I thought it was because the average career is 2 yeras vs an engineers beings 30 years. Do you have a favorite team?\nChunk 2: Assistant: Yeah that could be it, I do have a favorite team I love the Patriots I became a fan with the rb Benjarvus Green-ellis, crazy how he never fumbled, ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I thought it was because the average career is 2 yeras vs an engineers beings 30 years. Do you have a favorite team?", "role": "user", "streaming_reasoning": "The...
{ "answer": "Thats kind of demeaning, that shouldnt be a rule.What is your favorite football position?", "reasoning": "Across the dialogue, the user is asking for help with human: i thought it was because the average career is 2 yeras vs an engineers beings 30 years. Key context: Human: I thought it was because the...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_d8630df3-e052-486e-8852-804f60787ec6", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_001174
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah they make less then engineers, but then again their career is shorter", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That is what I figure it is, that the average career of a pro sports player is so much shorter.", "turn_id": 2 }, ...
{ "chunk_text": "Chunk 1: Human: Yeah they make less then engineers, but then again their career is shorter\nChunk 2: Assistant: That is what I figure it is, that the average career of a pro sports player is so much shorter.\nChunk 3: Human: Yeah. Did you know now they are using chips to track the players in the fiel...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah they make less then engineers, but then again their career is shorter", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Yeah. ...
{ "answer": "Yeah I read about that, I think it helps them develop better safety features as well.", "reasoning": "Across the dialogue, the user discusses \"Yeah they make less then engineers, but then again their.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversa...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_5d5d2df0-08ef-4130-8a8c-3d0ea3465c4b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004027
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "um i'm traveling to cambridge and i'm excited about seeing some local tourist attractions. i am also looking for a particular restaurant called the galleria.", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: um i'm traveling to cambridge and i'm excited about seeing some local tourist attractions. i am also looking for a particular restaurant called the galleria.\nChunk 3: yes, i'd like to book a table for four people at 1900 on monday, so 7 pm.", "dialogue_text": "Chunk 1: he...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is searching for particular restaurant called the galleria. Key context: um i'm traveling to cambridge and i'm excited about seeing some local tourist attractions; i am also looking for a partic...
{ "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": "MUL3964", "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_004028
train
audio
multi_turn
[ { "role": "user", "text": "i am. gle.", "turn_id": 1 }, { "role": "assistant", "text": "t o n.", "turn_id": 2 }, { "role": "user", "text": "pi.", "turn_id": 3 }, { "role": "assistant", "text": "5, 3, 1.", "turn_id": 4 }, { "role": "user", "text...
{ "chunk_text": "Chunk 1: i am. gle.\nChunk 2: t o n.\nChunk 3: pi.\nChunk 4: 5, 3, 1.\nChunk 5: at.\nChunk 6: outlook dot com.\nChunk 7: i want to book a taxi to commute between the two places.\nChunk 8: i want to leave the hotel by noon.", "dialogue_text": "Chunk 1: i am. gle.\nChunk 2: t o n.\nChunk 3: pi.\nChun...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i am. gle.", "role": "user", "streaming_reasoning": "The user mentions I am. gle. 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 wanting to book taxi to commute between the two places. Key context: outlook dot com; i want to book a taxi to commute between the two places; i want to leave t...
{ "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": "MUL3078", "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_004029
train
audio
multi_turn
[ { "role": "user", "text": "and i also once you have free wifi.", "turn_id": 1 }, { "role": "assistant", "text": "okay, i want to know the post code of this hotel.", "turn_id": 2 }, { "role": "user", "text": "okay, let me write down first.", "turn_id": 3 }, { "role...
{ "chunk_text": "Chunk 1: and i also once you have free wifi.\nChunk 2: okay, i want to know the post code of this hotel.\nChunk 3: okay, let me write down first.\nChunk 4: and how about the phone number of this hotel.\nChunk 5: okay. i'll call the hotel to know more details.\nChunk 6: yes, i'm also looking for a col...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and i also once you have free wifi.", "role": "user", "streaming_reasoning": "The user mentions And i also once you have free wifi. It is not yet clear whether the user ...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for college that is in the same area as the hotel. Key context: and i also once you have free wifi; okay, i want to know the post code of this hotel; okay, let me write down first...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "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": "MUL1223", "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_001175
train
audio
multi_turn
[ { "role": "user", "text": "Human: I am well, thanks. Do you play any instruments?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I used to play the piano and flute but haven't in a while. How about you? Did you know that there is a piano at the top of britain's highest mountain...
{ "chunk_text": "Chunk 1: Human: I am well, thanks. Do you play any instruments?\nChunk 2: Assistant: I used to play the piano and flute but haven't in a while. How about you? Did you know that there is a piano at the top of britain's highest mountain? It was discovered in 2006.\nChunk 3: Human: Wow. Who put it there...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I am well, thanks. Do you play any instruments?", "role": "user", "streaming_reasoning": "The user mentions Human: I am well, thanks. Do you play any instruments?...
{ "answer": "Hmm, I don't know if people know who put it there. No idea how it got there without people noticing. Ha.", "reasoning": "Across the dialogue, the user is asking for help with human: i am well, thanks. Key context: Human: I am well, thanks; Do you play any instruments; Assistant: I used to play the pian...
{ "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_2921fe56-d433-4355-86b5-da39f5b45e59", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004030
train
audio
multi_turn
[ { "role": "user", "text": "hello, can you help me.", "turn_id": 1 }, { "role": "assistant", "text": "i am planning on a trip and need information.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello, can you help me.\nChunk 2: i am planning on a trip and need information.", "dialogue_text": "Chunk 1: hello, can you help me.\nChunk 2: i am planning on a trip and need information.", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually reveale...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, can you help me.", "role": "user", "streaming_reasoning": "The user mentions Hello, can you help me. It is not yet clear whether the user needs the full scope of ...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user discusses \"hello, can you help me.\" over 2 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1727", "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_001176
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah. Did you know now they are using chips to track the players in the field?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah I read about that, I think it helps them develop better safety features as well.", "turn_id": 2 }, { ...
{ "chunk_text": "Chunk 1: Human: Yeah. Did you know now they are using chips to track the players in the field?\nChunk 2: Assistant: Yeah I read about that, I think it helps them develop better safety features as well.\nChunk 3: Human: Yes that makes sense. How about the radio, do you listen to it?", "dialogue_text...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah. Did you know now they are using chips to track the players in the field?", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Ye...
{ "answer": "Yeah I do, I found a good local station that I really like. How about yourself?", "reasoning": "Across the dialogue, the user discusses \"Yeah. Did you know now they are using chips to track the.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational...
{ "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_5d5d2df0-08ef-4130-8a8c-3d0ea3465c4b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004031
train
audio
multi_turn
[ { "role": "user", "text": "hi good afternoon i am looking for places to go to in town the attraction should be of the museum type and should be located", "turn_id": 1 }, { "role": "assistant", "text": "to the left of north and flesh", "turn_id": 2 }, { "role": "user", "text":...
{ "chunk_text": "Chunk 1: hi good afternoon i am looking for places to go to in town the attraction should be of the museum type and should be located\nChunk 2: to the left of north and flesh\nChunk 3: alright, great. could you give me the telephone number of maybe two of the museum.\nChunk 4: cafe. jello gallery.", ...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi good afternoon i am looking for places to go to in town the attraction should be of the museum type and should be located", "role": "user", "streaming_reasoning": "Th...
{ "answer": "Sure. I can provide the phone for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for places to go to in town the attraction should be of the museum type. Key context: hi good afternoon i am looking for places to go to in town the attraction should be of the m...
{ "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": "MUL3325", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004032
train
audio
multi_turn
[ { "role": "user", "text": "oh. pillow.", "turn_id": 1 }, { "role": "assistant", "text": "and saying things to themselves.", "turn_id": 2 }, { "role": "user", "text": "um i'm planning a trip in cameras and i'm looking for particular attractions.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: oh. pillow.\nChunk 2: and saying things to themselves.\nChunk 3: um i'm planning a trip in cameras and i'm looking for particular attractions.\nChunk 4: it's called cambridge contemporary art.\nChunk 5: um can i just get your phone number.\nChunk 6: no, it is.\nChunk 7: um can i use the tele...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "oh. pillow.", "role": "user", "streaming_reasoning": "The user mentions Oh. pillow. It is not yet clear whether the user needs the full scope of the user's request. The ...
{ "answer": "Sure. I can provide the phone for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for particular attractions. Key context: and saying things to themselves; um i'm planning a trip in cameras and i'm looking for particular attractions; it's called cambridge cont...
{ "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": "MUL2108", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004033
train
audio
multi_turn
[ { "role": "user", "text": "uh, only one people, thank you.", "turn_id": 1 }, { "role": "assistant", "text": "sure, 0 7 4 2.", "turn_id": 2 }, { "role": "user", "text": "7 7 9 6.", "turn_id": 3 }, { "role": "assistant", "text": "8. 2, 2, 2.", "turn_id": 4 ...
{ "chunk_text": "Chunk 1: uh, only one people, thank you.\nChunk 2: sure, 0 7 4 2.\nChunk 3: 7 7 9 6.\nChunk 4: 8. 2, 2, 2.\nChunk 5: 3, 3, 4, 2.\nChunk 6: okay, thank you so much.\nChunk 7: i'm also looking for a particular restaurant.\nChunk 8: uh, man's bar restaurant is the name.", "dialogue_text": "Chunk 1: uh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, only one people, thank you.", "role": "user", "streaming_reasoning": "The user mentions Uh, only one people, thank you. It is not yet clear whether the user needs th...
{ "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. Key context: uh, only one people, thank you; sure, 0 7 4 2; okay, thank you so much; i'm also looking for a particular restaurant. The answer shou...
{ "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": "MUL1726", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004034
train
audio
multi_turn
[ { "role": "user", "text": "5, 2, 4, 5.", "turn_id": 1 }, { "role": "assistant", "text": "0 5 0 9.", "turn_id": 2 }, { "role": "user", "text": "perfect. and i was also looking place for a place to dine.", "turn_id": 3 }, { "role": "assistant", "text": "i'd like...
{ "chunk_text": "Chunk 1: 5, 2, 4, 5.\nChunk 2: 0 5 0 9.\nChunk 3: perfect. and i was also looking place for a place to dine.\nChunk 4: i'd like a restaurant, an expensive restaurant. the central part of town.\nChunk 5: i like mexican food, ideally.\nChunk 6: yes. what about european cuisine then.\nChunk 7: sounds gr...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "5, 2, 4, 5.", "role": "user", "streaming_reasoning": "The user mentions 5, 2, 4, 5. It is not yet clear whether the user needs the full scope of the user's request. 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 wanting to book and i was also looking place for a place to dine. Key context: and i was also looking place for a place to dine; i'd like a restaurant, an expen...
{ "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": "MUL3385", "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_004035
train
audio
multi_turn
[ { "role": "user", "text": "okay. and do i need to pay for the ticket.", "turn_id": 1 }, { "role": "assistant", "text": "okay i got that and the i also want to find a hotel with a star of four maybe uh maybe with a an expensive price", "turn_id": 2 }, { "role": "user", "text":...
{ "chunk_text": "Chunk 1: okay. and do i need to pay for the ticket.\nChunk 2: okay i got that and the i also want to find a hotel with a star of four maybe uh maybe with a an expensive price\nChunk 3: okay.\nChunk 4: and.\nChunk 5: okay. and i would like it to be a guesthouse with free parking.\nChunk 6: oh, yes.\nC...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. and do i need to pay for the ticket.", "role": "user", "streaming_reasoning": "The user mentions Okay. and do i need to pay for the ticket. It is not yet clear whe...
{ "answer": "I can help book that. Could you provide the area?", "reasoning": "Across the dialogue, the user is searching for it for me. Key context: and do i need to pay for the ticket; okay i got that and the i also want to find a hotel with a star of four maybe uh maybe with a an expensive price okay; and i woul...
{ "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": "MUL1244", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004036
train
audio
multi_turn
[ { "role": "user", "text": "i'm looking for a train.", "turn_id": 1 }, { "role": "assistant", "text": "i will leave on monday, you know.", "turn_id": 2 }, { "role": "user", "text": "yes. and i will leave after fifteen forty five, please.", "turn_id": 3 }, { "role":...
{ "chunk_text": "Chunk 1: i'm looking for a train.\nChunk 2: i will leave on monday, you know.\nChunk 3: yes. and i will leave after fifteen forty five, please.\nChunk 4: yes. and i will depart from a name, a place named c. e. m. b. or something.\nChunk 5: yes, cambridge is right.\nChunk 6: and i will go to a, please...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm looking for a train.", "role": "user", "streaming_reasoning": "The user mentions I'm looking for a train. It is not yet clear whether the user needs the full scope o...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: i'm looking for a train; i will leave on monday, you know; and i will leave after fifteen forty five, please; and i will depart from a name, a place named c. Th...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3925", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_001177
train
audio
multi_turn
[ { "role": "user", "text": "Human: He had a genius understanding of language. the words he created just seemed to have the right sound and meaning. he changed language singlehandedly.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes if only he had lived longer, I wonder what o...
{ "chunk_text": "Chunk 1: Human: He had a genius understanding of language. the words he created just seemed to have the right sound and meaning. he changed language singlehandedly.\nChunk 2: Assistant: Yes if only he had lived longer, I wonder what other inventions of the English language he could have made, he died...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: He had a genius understanding of language. the words he created just seemed to have the right sound and meaning. he changed language singlehandedly.", "role": "user", ...
{ "answer": "Yes I agree, on a happier note though do you ever watch any comedies? That could include black comedies as well", "reasoning": "Across the dialogue, the user discusses \"He had a genius understanding of language. the words he.\" over 3 turns. The answer should respond to the latest user turn naturally,...
{ "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": "MultiDialog", "dialogue_id": "t_06cbe297-3509-489a-ae66-ab44fe99ba65", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004037
train
audio
multi_turn
[ { "role": "user", "text": "hello, okay, hear me.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i need a taxi. i'm gonna depart from abc theater. i'm going to visit cambridge, which is the i double d.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello, okay, hear me.\nChunk 2: hi, i need a taxi. i'm gonna depart from abc theater. i'm going to visit cambridge, which is the i double d.", "dialogue_text": "Chunk 1: hello, okay, hear me.\nChunk 2: hi, i need a taxi. i'm gonna depart from abc theater. i'm going to visit cambridge, whic...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, okay, hear me.", "role": "user", "streaming_reasoning": "The user mentions Hello, okay, hear me. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help with the taxi. Could you share the time?", "reasoning": "Across the dialogue, the user is talking about taxi. Key context: hello, okay, hear me; hi, i need a taxi; i'm gonna depart from abc theater; i'm going to visit cambridge, which is the i double d. The answer should focus on the latest ...
{ "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": "SNG0413", "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_004038
train
audio
multi_turn
[ { "role": "user", "text": "yes, yes, kingsland. yes, thank you so much.", "turn_id": 1 }, { "role": "assistant", "text": "okay, okay, that's the last. hello. hi, excuse me. can i please make a booking for the summer month of people then.", "turn_id": 2 }, { "role": "user", "t...
{ "chunk_text": "Chunk 1: yes, yes, kingsland. yes, thank you so much.\nChunk 2: okay, okay, that's the last. hello. hi, excuse me. can i please make a booking for the summer month of people then.\nChunk 3: yes, sir mahari number it is 1 2.\nChunk 4: 6 farm error.\nChunk 5: 4 7, 0.\nChunk 6: 9 2 0.\nChunk 7: 6 double...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, yes, kingsland. yes, thank you so much.", "role": "user", "streaming_reasoning": "The user mentions Yes, yes, kingsland. yes, thank you so much. It is not yet clear...
{ "answer": "Sure. I can provide the id for the matching train option.", "reasoning": "Across the dialogue, the user is wanting to book yes, yes, kingsland. Key context: yes, yes, kingsland; yes, thank you so much; okay, okay, that's the last; hi, excuse me. The answer should focus on the latest user turn while inc...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3553", "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_004039
train
audio
multi_turn
[ { "role": "user", "text": "and should arrive preferably, um i have an event at half past one. so.", "turn_id": 1 }, { "role": "assistant", "text": "a few minutes earlier.", "turn_id": 2 }, { "role": "user", "text": "and it should depart from london liverpool street and go to ...
{ "chunk_text": "Chunk 1: and should arrive preferably, um i have an event at half past one. so.\nChunk 2: a few minutes earlier.\nChunk 3: and it should depart from london liverpool street and go to cambridge.\nChunk 4: that's perfect.\nChunk 5: um yes, please, for 7 people.\nChunk 6: 8 9 5 0.\nChunk 7: 5 0 6 2.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and should arrive preferably, um i have an event at half past one. so.", "role": "user", "streaming_reasoning": "The user mentions And should arrive preferably, um i hav...
{ "answer": "I can help with the train. Could you share the day?", "reasoning": "Across the dialogue, the user is talking about and should arrive preferably, um i have an event at half past one. Key context: and should arrive preferably, um i have an event at half past one; a few minutes earlier; and it should depa...
{ "category": "creative_planning", "subcategory": "event_idea", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2822", "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_004040
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i. hi, hello. can you hear me.", "turn_id": 2 }, { "role": "user", "text": "all right. so i'm hoping that you'll be able to help me. i am in an age if i need some information, please.", "t...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i. hi, hello. can you hear me.\nChunk 3: all right. so i'm hoping that you'll be able to help me. i am in an age if i need some information, please.\nChunk 4: so 1st of all, i'm looking for some place to eat, please.", "dialogue_text": "Chunk 1: hello.\nChunk 2: i. hi, 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 with the restaurant. Could you share the area, food, price?", "reasoning": "Across the dialogue, the user is searching for place to eat. Key context: can you hear me; so i'm hoping that you'll be able to help me; i am in an age if i need some information, please; so 1st of all, i'm looking f...
{ "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": "MUL2034", "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_004041
train
audio
multi_turn
[ { "role": "user", "text": "2 3, 7 2 6.", "turn_id": 1 }, { "role": "assistant", "text": "7 5 9 2. 5 4 did you get.", "turn_id": 2 }, { "role": "user", "text": "that is correct.", "turn_id": 3 }, { "role": "assistant", "text": "perfect. i'm craving some spicy f...
{ "chunk_text": "Chunk 1: 2 3, 7 2 6.\nChunk 2: 7 5 9 2. 5 4 did you get.\nChunk 3: that is correct.\nChunk 4: perfect. i'm craving some spicy food.\nChunk 5: a place to dine in the center with cheap food.\nChunk 6: i will hold.\nChunk 7: you're welcome.\nChunk 8: great. may i book it for the two of us, please.", "...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "2 3, 7 2 6.", "role": "user", "streaming_reasoning": "The user mentions 2 3, 7 2 6. It is not yet clear whether the user needs the full scope of the user's request. The ...
{ "answer": "I can help book that. Could you provide the day, time?", "reasoning": "Across the dialogue, the user is wanting to book it for the two of us. Key context: 5 4 did you get; that is correct; i'm craving some spicy food; a place to dine in the center with cheap food. The answer should focus on the latest ...
{ "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": "MUL2828", "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_004042
train
audio
multi_turn
[ { "role": "user", "text": "hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm good thank you um i would like to i would like to book for a train that is committing on monday from snakes to", "turn_id": 2 }, { "role": "user", "text": "cambridge and shoul...
{ "chunk_text": "Chunk 1: hello, how are you.\nChunk 2: i'm good thank you um i would like to i would like to book for a train that is committing on monday from snakes to\nChunk 3: cambridge and should arrive 4 32 pm\nChunk 4: alright, so i'd like to book for five people.\nChunk 5: yes, it's 6 6, 3, 7.\nChunk 6: 3 3 ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Hello, how are you. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "I can help 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 for a train that is committing on monday from snakes to cambridge. Key context: hello, how are you; i'm good thank you um i would like to i woul...
{ "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": "MUL0344", "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_004043
train
audio
multi_turn
[ { "role": "user", "text": "um alright, also. um can you find me 1? have a star of 4 and i'd like to, um, get a gift hub.", "turn_id": 1 }, { "role": "assistant", "text": "okay.", "turn_id": 2 }, { "role": "user", "text": "um okay, that would be great.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: um alright, also. um can you find me 1? have a star of 4 and i'd like to, um, get a gift hub.\nChunk 2: okay.\nChunk 3: um okay, that would be great.\nChunk 4: murder.\nChunk 5: okay, great. can you give me the phone number.\nChunk 6: perfect. um also can you book a taxi for me to commute be...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um alright, also. um can you find me 1? have a star of 4 and i'd like to, um, get a gift hub.", "role": "user", "streaming_reasoning": "The user mentions searching for 1...
{ "answer": "I can help book that. Could you provide the departure, destination?", "reasoning": "Across the dialogue, the user is searching for taxi for me to commute between the two places. Key context: um alright, also; um can you find me 1; have a star of 4 and i'd like to, um, get a gift hub; um okay, that woul...
{ "category": "finance_consumer", "subcategory": "budget_planning", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0212", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004044
train
audio
multi_turn
[ { "role": "user", "text": "are you. hello, how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm well, thank you. my name is jill jordan and i'm looking for some information about the trip to cambridge.", "turn_id": 2 }, { "role": "user", "text": "so firstly, i a...
{ "chunk_text": "Chunk 1: are you. hello, how are you.\nChunk 2: i'm well, thank you. my name is jill jordan and i'm looking for some information about the trip to cambridge.\nChunk 3: so firstly, i am looking for a place to stay. the hotel doesn't have to have free parking and should be in the north.\nChunk 4: okay....
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "are you. hello, how are you.", "role": "user", "streaming_reasoning": "The user mentions Are you. hello, how are you. It is not yet clear whether the user needs the full...
{ "answer": "I can help with the hotel. Could you share the hotel_type?", "reasoning": "Across the dialogue, the user is searching for information about the trip to cambridge. Key context: hello, how are you; i'm well, thank you; my name is jill jordan and i'm looking for some information about the trip to cambridg...
{ "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": "MUL2269", "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_004045
train
audio
multi_turn
[ { "role": "user", "text": "hello, i need some help.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a train.", "turn_id": 2 }, { "role": "user", "text": "yes. and i think the train should leave on monday.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hello, i need some help.\nChunk 2: yes, i'm looking for a train.\nChunk 3: yes. and i think the train should leave on monday.", "dialogue_text": "Chunk 1: hello, i need some help.\nChunk 2: yes, i'm looking for a train.\nChunk 3: yes. and i think the train should leave on monday.", "inst...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, i need some help.", "role": "user", "streaming_reasoning": "The user mentions Hello, i need some help. It is not yet clear whether the user needs the full scope o...
{ "answer": "I can help with the train. Could you share the departure, destination, time?", "reasoning": "Across the dialogue, the user is searching for train. Key context: hello, i need some help; yes, i'm looking for a train; and i think the train should leave on monday. The answer should focus on the latest user...
{ "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": "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_004046
train
audio
multi_turn
[ { "role": "user", "text": "yes.", "turn_id": 1 }, { "role": "assistant", "text": "the the train should also leave on wednesday and should depart from the city on the east midland.", "turn_id": 2 }, { "role": "user", "text": "yes, man.", "turn_id": 3 }, { "role": "...
{ "chunk_text": "Chunk 1: yes.\nChunk 2: the the train should also leave on wednesday and should depart from the city on the east midland.\nChunk 3: yes, man.\nChunk 4: okay, i got that man. thank you.\nChunk 5: the train should leave on wednesday. and should depart from i mean, i want to make a booking for 7 people....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes.", "role": "user", "streaming_reasoning": "The user mentions Yes. It is not yet clear whether the user needs the full scope of the user's request. The assistant shou...
{ "answer": "I can help book that. Could you provide the destination?", "reasoning": "Across the dialogue, the user is wanting to book to make a booking for 7 people. Key context: the the train should also leave on wednesday and should depart from the city on the east midland; okay, i got that man; the train 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": "MUL0972", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004047
train
audio
multi_turn
[ { "role": "user", "text": "h hotel. our fulltime.", "turn_id": 1 }, { "role": "assistant", "text": "i for india. t for tango.", "turn_id": 2 }, { "role": "user", "text": "zeta fuzzy.", "turn_id": 3 }, { "role": "assistant", "text": "uh, yeah, um. i'm wondering...
{ "chunk_text": "Chunk 1: h hotel. our fulltime.\nChunk 2: i for india. t for tango.\nChunk 3: zeta fuzzy.\nChunk 4: uh, yeah, um. i'm wondering, are there any museums in the east of cambridge there.\nChunk 5: okay.\nChunk 6: alright, and what is the interest for you.\nChunk 7: okay, fantastic. um, i do also need to ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "h hotel. our fulltime.", "role": "user", "streaming_reasoning": "The user mentions H hotel. our fulltime. It is not yet clear whether the user needs the full scope of th...
{ "answer": "I can help book that. Could you provide the departure, destination, time?", "reasoning": "Across the dialogue, the user is wanting to book taxi. Key context: our fulltime; i for india; t for tango; uh, yeah, um. The answer should focus on the latest user turn while incorporating relevant context from e...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "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_multidialog_v02_001178
train
audio
multi_turn
[ { "role": "user", "text": "Human: I am not sure. If they did, they would be even better!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I wonder if they are friendly to the big mean dogs too, I suspect not", "turn_id": 2 }, { "role": "user", "text": "Human: Prob...
{ "chunk_text": "Chunk 1: Human: I am not sure. If they did, they would be even better!\nChunk 2: Assistant: I wonder if they are friendly to the big mean dogs too, I suspect not\nChunk 3: Human: Probably not. The C-Suite probably can bring dogs but not the entry level jobs.", "dialogue_text": "Chunk 1: Human: I am...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I am not sure. If they did, they would be even better!", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not yet clear whethe...
{ "answer": "Dogs were among the first animals to be domesticated", "reasoning": "Across the dialogue, the user discusses \"I am not sure. If they did, they would be even.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Ac...
{ "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_cdbe8ade-c8d4-4538-8739-007443fb9f2b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_001179
train
audio
multi_turn
[ { "role": "user", "text": "Human: do you like football?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I'm a fan of all sports, but football happens to be one of my favorites and I follow the NFL closely. You?", "turn_id": 2 }, { "role": "user", "text": "Human: ...
{ "chunk_text": "Chunk 1: Human: do you like football?\nChunk 2: Assistant: I'm a fan of all sports, but football happens to be one of my favorites and I follow the NFL closely. You?\nChunk 3: Human: I don't really watch it that much. I did watch the Super Bowl which is the first Sunday in February.", "dialogue_tex...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: do you like football?", "role": "user", "streaming_reasoning": "The user mentions Human: do you like football?. It is not yet clear whether the user needs what sp...
{ "answer": "Oh, did you hear anything about what's been going with Le'Veon Bell this past season?", "reasoning": "Across the dialogue, the user discusses \"do you like football?\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reason...
{ "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_24e90986-8199-43ce-93df-f9946a4dc3e6", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004048
train
audio
multi_turn
[ { "role": "user", "text": "jean quarter.", "turn_id": 1 }, { "role": "assistant", "text": "see. a r. ti. e r.", "turn_id": 2 }, { "role": "user", "text": "okay. um, yeah, it's 5 7. 5 0, 0.", "turn_id": 3 }, { "role": "assistant", "text": "7 5 3 2.", "turn_...
{ "chunk_text": "Chunk 1: jean quarter.\nChunk 2: see. a r. ti. e r.\nChunk 3: okay. um, yeah, it's 5 7. 5 0, 0.\nChunk 4: 7 5 3 2.\nChunk 5: yes, that's correct.\nChunk 6: okay. um, it's jay carter. q g 1 i.\nChunk 7: yes, at outlook dot com.\nChunk 8: oh, yes. um, may you book a room at the lovell lodge. for me, pl...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "jean quarter.", "role": "user", "streaming_reasoning": "The user mentions Jean quarter. 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 area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book room at the lovell lodge. Key context: jean quarter; um, yeah, it's 5 7; yes, that's correct; um, it's jay carter. The answer should focus on the latest user turn while ...
{ "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": "MUL0782", "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_004049
train
audio
multi_turn
[ { "role": "user", "text": "i truly as well speaking.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for a restaurant, should serve a mexican food and should be in the center of the city.", "turn_id": 2 }, { "role": "user", "text": "okay.", "turn_id": 3 },...
{ "chunk_text": "Chunk 1: i truly as well speaking.\nChunk 2: i'm looking for a restaurant, should serve a mexican food and should be in the center of the city.\nChunk 3: okay.\nChunk 4: yes, i'm still here.\nChunk 5: okay. how about. that. saves chinese food.\nChunk 6: okay.\nChunk 7: yes.\nChunk 8: 2 people. uh, be...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i truly as well speaking.", "role": "user", "streaming_reasoning": "The user mentions I truly as well speaking. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help with the restaurant. Could you share the price?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: i truly as well speaking; i'm looking for a restaurant, should serve a mexican food and should be in the center of the city; yes, i'm still here; saves chin...
{ "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": "MUL3511", "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_004050
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for a restaurant.", "turn_id": 2 }, { "role": "user", "text": "yes. uh, i prefer expensive price range.", "turn_id": 3 }, { "role": "assistant", "text": "and i...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a restaurant.\nChunk 3: yes. uh, i prefer expensive price range.\nChunk 4: and i want more convenient traffic.", "dialogue_text": "Chunk 1: hello.\nChunk 2: yes, i'm looking for a restaurant.\nChunk 3: yes. uh, i prefer expensive price range.\nChunk 4:...
{ "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, food?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: yes, i'm looking for a restaurant; uh, i prefer expensive price range; and i want more convenient traffic. The answer should focus on the latest user 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": "MUL0671", "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_004051
train
audio
multi_turn
[ { "role": "user", "text": "preferably on the western side is also.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i call it.", "turn_id": 2 }, { "role": "user", "text": "i'll prepare maybe something that has to do with like a.", "turn_id": 3 }, { "role": "...
{ "chunk_text": "Chunk 1: preferably on the western side is also.\nChunk 2: yes, i call it.\nChunk 3: i'll prepare maybe something that has to do with like a.\nChunk 4: yes, that is product.\nChunk 5: i'm only looking for the information, preferably the postcode.\nChunk 6: ok.\nChunk 7: alright, thanks a lot.\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "preferably on the western side is also.", "role": "user", "streaming_reasoning": "The user mentions Preferably on the western side is also. 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. Key context: preferably on the western side is also; yes, i call it; i'll prepare maybe something that has to do with like a; yes, that is product. The...
{ "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": "MUL1407", "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_001180
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah I don't remember him either. I do like Baker Mayfield, he's good at video games and he was going to be a professional video game player, I was also good at video games back in college LOL", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Well...
{ "chunk_text": "Chunk 1: Human: Yeah I don't remember him either. I do like Baker Mayfield, he's good at video games and he was going to be a professional video game player, I was also good at video games back in college LOL\nChunk 2: Assistant: Well, not as likely to get seriously injured with video games. I like N...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah I don't remember him either. I do like Baker Mayfield, he's good at video games and he was going to be a professional video game player, I was also good at video games b...
{ "answer": "I actually don't know much about him other than is smart academically. I did learn that Snoop Dog did his son's HS fight song...", "reasoning": "Across the dialogue, the user is wanting to book human: yeah i don't remember him either. Key context: Human: Yeah I don't remember him either; I like ND's co...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_6d4f92f5-a83e-4210-9a69-5e5475bf14b1", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_001181
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yes I want to watch that score! It sounds incredible what do you think about a deaf quarterback creating the circular huddle?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: That is interesting. I wonder how he was able to play QB? Admirable... ...
{ "chunk_text": "Chunk 1: Human: Yes I want to watch that score! It sounds incredible what do you think about a deaf quarterback creating the circular huddle?\nChunk 2: Assistant: That is interesting. I wonder how he was able to play QB? Admirable... Do you enjoy watching dramas when you aren't watching football?\nCh...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yes I want to watch that score! It sounds incredible what do you think about a deaf quarterback creating the circular huddle?", "role": "user", "streaming_reasoni...
{ "answer": "I like him a lot. I also like Patrick Stewart -- he teaches master drama classes in the UK.", "reasoning": "Across the dialogue, the user discusses \"Yes I want to watch that score! It sounds incredible what.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the c...
{ "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_6d4f92f5-a83e-4210-9a69-5e5475bf14b1", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004052
train
audio
multi_turn
[ { "role": "user", "text": "hmm, sure. my phone number. 0, 1, 3.", "turn_id": 1 }, { "role": "assistant", "text": "double 5 9.", "turn_id": 2 }, { "role": "user", "text": "8 4 0.", "turn_id": 3 }, { "role": "assistant", "text": "0.", "turn_id": 4 }, { ...
{ "chunk_text": "Chunk 1: hmm, sure. my phone number. 0, 1, 3.\nChunk 2: double 5 9.\nChunk 3: 8 4 0.\nChunk 4: 0.\nChunk 5: thank you so much.\nChunk 6: well, i suppose that's often. offer this afternoon.\nChunk 7: hmm, that's why i be nice about you.\nChunk 8: then good-by.", "dialogue_text": "Chunk 1: hmm, sure....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hmm, sure. my phone number. 0, 1, 3.", "role": "user", "streaming_reasoning": "The user mentions Hmm, sure. my phone number. 0, 1, 3. It is not yet clear whether the use...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is asking for recommendations about my phone number. Key context: my phone number; thank you so much; well, i suppose that's often; offer this afternoon. 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": "SNG0041", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004053
train
audio
multi_turn
[ { "role": "user", "text": "hello. is that customer service.", "turn_id": 1 }, { "role": "assistant", "text": "i am traveling to cambridge and i'm looking for a place to dine.", "turn_id": 2 }, { "role": "user", "text": "ah the restaurant should be in cheap price range and sho...
{ "chunk_text": "Chunk 1: hello. is that customer service.\nChunk 2: i am traveling to cambridge and i'm looking for a place to dine.\nChunk 3: ah the restaurant should be in cheap price range and should serve seafood.\nChunk 4: uh, well, so what about. modern european food.\nChunk 5: ah okay, that's great. so i want...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. is that customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello. is that customer service. It is not yet clear whether the user needs ...
{ "answer": "I can help book that. Could you provide the area, day, time?", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: is that customer service; i am traveling to cambridge and i'm looking for a place to dine; ah the restaurant should be in cheap price range and should ...
{ "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": "MUL0986", "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_004054
train
audio
multi_turn
[ { "role": "user", "text": "hi, this is joanna speaking.", "turn_id": 1 }, { "role": "assistant", "text": "and great things in yourself.", "turn_id": 2 }, { "role": "user", "text": "i'm planning a trip to cambridge and i need some information on trains. this is something that ...
{ "chunk_text": "Chunk 1: hi, this is joanna speaking.\nChunk 2: and great things in yourself.\nChunk 3: i'm planning a trip to cambridge and i need some information on trains. this is something that you can help with.\nChunk 4: so i'm looking for a train that should depart from cambridge. going to stanstead airport....
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, this is joanna speaking.", "role": "user", "streaming_reasoning": "The user mentions Hi, this is joanna speaking. It is not yet clear whether the user needs the full...
{ "answer": "Sure. I can provide the arriveby for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train that should depart from cambridge. Key context: hi, this is joanna speaking; and great things in yourself; i'm planning a trip to cambridge and i need some information on...
{ "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": "MUL3677", "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_004055
train
audio
multi_turn
[ { "role": "user", "text": "um i prefer a place that serves modern european food peace.", "turn_id": 1 }, { "role": "assistant", "text": "i need to embrace some people, so it needs to be.", "turn_id": 2 }, { "role": "user", "text": "all right. yeah, you can tell me what area o...
{ "chunk_text": "Chunk 1: um i prefer a place that serves modern european food peace.\nChunk 2: i need to embrace some people, so it needs to be.\nChunk 3: all right. yeah, you can tell me what area of cambridge is that in.\nChunk 4: lovely. and what is the post code, please.\nChunk 5: perfect and the phone number, p...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um i prefer a place that serves modern european food peace.", "role": "user", "streaming_reasoning": "The user mentions Um i prefer a place that serves modern european f...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for train. Key context: um i prefer a place that serves modern european food peace; i need to embrace some people, so it needs to be; yeah, you can tell me what area of...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "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_004056
train
audio
multi_turn
[ { "role": "user", "text": "uh, can we make it for monday quarter to 6 in the evening and.", "turn_id": 1 }, { "role": "assistant", "text": "um what about sunday.", "turn_id": 2 }, { "role": "user", "text": "yes. at quarter to 6.", "turn_id": 3 }, { "role": "assist...
{ "chunk_text": "Chunk 1: uh, can we make it for monday quarter to 6 in the evening and.\nChunk 2: um what about sunday.\nChunk 3: yes. at quarter to 6.\nChunk 4: yes, please. can you look at the system books. parking spots at both the hotel as well as the restaurant.\nChunk 5: so it is orpha romeo if for fox.\nChunk...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, can we make it for monday quarter to 6 in the evening and.", "role": "user", "streaming_reasoning": "The user mentions talking about 6. It is not yet clear whether t...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is wanting to book uh, can we make it for monday quarter to 6 in the evening and. Key context: uh, can we make it for monday quarter to 6 in the evening and; um what about sunday; at qu...
{ "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": "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_004057
train
audio
multi_turn
[ { "role": "user", "text": "hello, good afternoon.", "turn_id": 1 }, { "role": "assistant", "text": "yes, ma'am, i'm playing playing in my trip in cambridge and i'm looking for a train.", "turn_id": 2 }, { "role": "user", "text": "yes, the trend should go to the university and...
{ "chunk_text": "Chunk 1: hello, good afternoon.\nChunk 2: yes, ma'am, i'm playing playing in my trip in cambridge and i'm looking for a train.\nChunk 3: yes, the trend should go to the university and should leave on friday.", "dialogue_text": "Chunk 1: hello, good afternoon.\nChunk 2: yes, ma'am, i'm playing playi...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, good afternoon.", "role": "user", "streaming_reasoning": "The user mentions Hello, good afternoon. It is not yet clear whether the user needs the full scope of th...
{ "answer": "I can help with the train. Could you share the departure, time?", "reasoning": "Across the dialogue, the user is searching for train. Key context: hello, good afternoon; yes, ma'am, i'm playing playing in my trip in cambridge and i'm looking for a train; yes, the trend should go to the university and s...
{ "category": "education", "subcategory": "course_planning", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1093", "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_001182
train
audio
multi_turn
[ { "role": "user", "text": "Human: I have not and I bet you Georgia Tech are bragging about that to this day", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes and I pretty sure that was cumberland coach last coaching season. I know they got teased for days.", "turn_id": 2 ...
{ "chunk_text": "Chunk 1: Human: I have not and I bet you Georgia Tech are bragging about that to this day\nChunk 2: Assistant: Yes and I pretty sure that was cumberland coach last coaching season. I know they got teased for days.\nChunk 3: Human: Yeah, pretty sad day for them. On another topic, do you know much abou...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I have not and I bet you Georgia Tech are bragging about that to this day", "role": "user", "streaming_reasoning": "The user mentions talking about Human, Georgia...
{ "answer": "Yes try to read the bible a lot, my favorite chapter is Psalm. I also learn certain verses. what about you, do you read the bible?", "reasoning": "Across the dialogue, the user discusses \"I have not and I bet you Georgia Tech are bragging about.\" over 3 turns. The answer should respond to the latest ...
{ "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_9070284f-e8ee-4ff6-82e4-ec55607c5379", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004058
train
audio
multi_turn
[ { "role": "user", "text": "my name is elizabeth catherine.", "turn_id": 1 }, { "role": "assistant", "text": "okay, is. e l i s.", "turn_id": 2 }, { "role": "user", "text": "a b e t h.", "turn_id": 3 }, { "role": "assistant", "text": "and then c a s t.", "t...
{ "chunk_text": "Chunk 1: my name is elizabeth catherine.\nChunk 2: okay, is. e l i s.\nChunk 3: a b e t h.\nChunk 4: and then c a s t.\nChunk 5: l e m a n.\nChunk 6: okay, my email address is c a s t.\nChunk 7: yeah. and then l e m a n.\nChunk 8: mm. and then one end is that, ah.", "dialogue_text": "Chunk 1: my na...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "my name is elizabeth catherine.", "role": "user", "streaming_reasoning": "The user mentions My name is elizabeth catherine. It is not yet clear whether the user needs th...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is talking about my name is elizabeth catherine. Key context: my name is elizabeth catherine; and then c a s t; okay, my email address is c a s t; and then l e m a n. The answer should focus on the latest us...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1192", "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_004059
train
audio
multi_turn
[ { "role": "user", "text": "um.", "turn_id": 1 }, { "role": "assistant", "text": "ah yes.", "turn_id": 2 }, { "role": "user", "text": "are from cambridge.", "turn_id": 3 }, { "role": "assistant", "text": "i. do you know the football's team's nickname is the por...
{ "chunk_text": "Chunk 1: um.\nChunk 2: ah yes.\nChunk 3: are from cambridge.\nChunk 4: i. do you know the football's team's nickname is the porches.\nChunk 5: it.\nChunk 6: yes.\nChunk 7: yes, correct.\nChunk 8: yes.", "dialogue_text": "Chunk 1: um.\nChunk 2: ah yes.\nChunk 3: are from cambridge.\nChunk 4: i. do y...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um.", "role": "user", "streaming_reasoning": "The user mentions Um. 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 day, time?", "reasoning": "Across the dialogue, the user is talking about are from cambridge. Key context: are from cambridge; do you know the football's team's nickname is the porches; yes, correct. The answer should focus on the latest user turn while in...
{ "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": "MUL1806", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004060
train
audio
multi_turn
[ { "role": "user", "text": "and i'm looking for a boat type of place to visit in town.", "turn_id": 1 }, { "role": "assistant", "text": "ok, not a problem.", "turn_id": 2 }, { "role": "user", "text": "oh, great. um, can i please have the postal code.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: and i'm looking for a boat type of place to visit in town.\nChunk 2: ok, not a problem.\nChunk 3: oh, great. um, can i please have the postal code.\nChunk 4: and then the entrance fee.\nChunk 5: okay, excellent. and what is their phone number.\nChunk 6: okay, thank you very much.\nChunk 7: o...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and i'm looking for a boat type of place to visit in town.", "role": "user", "streaming_reasoning": "The user mentions And i'm looking for a boat type of place to visit ...
{ "answer": "Sure. I can help with the postcode, phone; first I need to identify the right restaurant option.", "reasoning": "Across the dialogue, the user is searching for boat type of place to visit in town. Key context: and i'm looking for a boat type of place to visit in town; ok, not a problem; um, can i pleas...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0877", "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_004061
train
audio
multi_turn
[ { "role": "user", "text": "hello, can you hear me.", "turn_id": 1 }, { "role": "assistant", "text": "is that customer service.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "i will go to ...
{ "chunk_text": "Chunk 1: hello, can you hear me.\nChunk 2: is that customer service.\nChunk 3: i'm looking for a train.\nChunk 4: i will go to ellie.\nChunk 5: yes. and we'll leave on wednesday.\nChunk 6: yes. and i will depart from cambridge.\nChunk 7: yes, i will arrive by sixteen, forty five.\nChunk 8: yes, that'...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, can you hear me.", "role": "user", "streaming_reasoning": "The user mentions Hello, can you hear me. It is not yet clear whether the user needs the full scope of ...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: hello, can you hear me; is that customer service; i'm looking for a train; i will go to ellie. The answer should focus on the latest user turn while incorporati...
{ "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": "MUL3927", "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_004062
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi i'm planning a trip to cambridge i'm looking for a place to dine and i'd like something in the expensive price range and i'd", "turn_id": 2 }, { "role": "user", "text": "like it in t...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: hi i'm planning a trip to cambridge i'm looking for a place to dine and i'd like something in the expensive price range and i'd\nChunk 3: like it in the south part of town and serving queensland perhaps from central america area\nChunk 4: sounds great. i'd like a book...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: i'd like a book; please, for four people at one pm on thursday, december twenty ninth; yes, my name is; nora mitchell ...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2913", "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_001183
train
audio
multi_turn
[ { "role": "user", "text": "Human: That probably has more do with him being a Scientologist than anything - and the most popular member of that religion to boot!", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah I heard of that. He did etch Katie Holmes name on the top of the ...
{ "chunk_text": "Chunk 1: Human: That probably has more do with him being a Scientologist than anything - and the most popular member of that religion to boot!\nChunk 2: Assistant: Yeah I heard of that. He did etch Katie Holmes name on the top of the Burj Khalifa building. That's wacky so...\nChunk 3: Human: All this...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: That probably has more do with him being a Scientologist than anything - and the most popular member of that religion to boot!", "role": "user", "streaming_reason...
{ "answer": "Yes, but I too am having to rethink him. I really did like him in Risky Business back in the day. He actually does his stunts like hanging from a plane at 5,000 feet in the newest MI.", "reasoning": "Across the dialogue, the user is asking for help with shower. Key context: Human: That probably has mor...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_b96704d0-0a7a-4b25-8d11-93d1ead8f229", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004063
train
audio
multi_turn
[ { "role": "user", "text": "perfect. if i could just have the address please and post code.", "turn_id": 1 }, { "role": "assistant", "text": "got it. thank you.", "turn_id": 2 }, { "role": "user", "text": "yes, i'm also looking for a train, please. and i needed to leave. let's...
{ "chunk_text": "Chunk 1: perfect. if i could just have the address please and post code.\nChunk 2: got it. thank you.\nChunk 3: yes, i'm also looking for a train, please. and i needed to leave. let's see it after sunday, october.\nChunk 4: and going from cambridge to london liverpool street. arriving by 9 45 am.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "perfect. if i could just have the address please and post code.", "role": "user", "streaming_reasoning": "The user mentions talking about Perfect. It is not yet clear wh...
{ "answer": "Sure. I can provide the travel_time, ticket, leaveat for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train. Key context: if i could just have the address please and post code; yes, i'm also looking for a train, please; and i needed to leave; let's see it af...
{ "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": "MUL3389", "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_004064
train
audio
multi_turn
[ { "role": "user", "text": "hello is that customer service center.", "turn_id": 1 }, { "role": "assistant", "text": "ah yes i'm planning my trip in cambridge and now i'm looking for places to go in town could you please help me to find a attraction", "turn_id": 2 }, { "role": "use...
{ "chunk_text": "Chunk 1: hello is that customer service center.\nChunk 2: ah yes i'm planning my trip in cambridge and now i'm looking for places to go in town could you please help me to find a attraction\nChunk 3: yes, i think the attraction should be in the west.\nChunk 4: i think any type is okay.\nChunk 5: okay...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello is that customer service center.", "role": "user", "streaming_reasoning": "The user mentions Hello is that customer service center. It is not yet clear whether the...
{ "answer": "I can help with the attraction. Could you share the type?", "reasoning": "Across the dialogue, the user is searching for places to go in town could you please help me to find a attraction yes. Key context: hello is that customer service center; ah yes i'm planning my trip in cambridge and now i'm looki...
{ "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": "MUL1784", "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_004065
train
audio
multi_turn
[ { "role": "user", "text": "i'm dick and thank.", "turn_id": 1 }, { "role": "assistant", "text": "can you help me with the trending.", "turn_id": 2 }, { "role": "user", "text": "oh, that's one news.", "turn_id": 3 }, { "role": "assistant", "text": "i'm driving ...
{ "chunk_text": "Chunk 1: i'm dick and thank.\nChunk 2: can you help me with the trending.\nChunk 3: oh, that's one news.\nChunk 4: i'm driving to carriage.\nChunk 5: will be leaving. i am an orange gentleman.\nChunk 6: i hope that will work just fine.\nChunk 7: i want to be set today.\nChunk 8: is there anything ava...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm dick and thank.", "role": "user", "streaming_reasoning": "The user mentions I'm dick and thank. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "I can help with the train. Could you share the time?", "reasoning": "Across the dialogue, the user is asking for help with to be set today. Key context: i'm dick and thank; can you help me with the trending; oh, that's one news; i'm driving to carriage. The answer should focus on the latest user turn w...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0051", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004066
train
audio
multi_turn
[ { "role": "user", "text": "yes, we are. i'm also looking for a train.", "turn_id": 1 }, { "role": "assistant", "text": "yes, it's 15 hours now. and the the train should go to cambridge and should should arrive in 30 minutes.", "turn_id": 2 }, { "role": "user", "text": "yes.",...
{ "chunk_text": "Chunk 1: yes, we are. i'm also looking for a train.\nChunk 2: yes, it's 15 hours now. and the the train should go to cambridge and should should arrive in 30 minutes.\nChunk 3: yes.\nChunk 4: the the train should also leave on wednesday and should depart from the city on the east midland.\nChunk 5: y...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, we are. i'm also looking for a train.", "role": "user", "streaming_reasoning": "The user mentions Yes, we are. i'm also looking for a train. It is not yet clear whe...
{ "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, we are; i'm also looking for a train; yes, it's 15 hours now; and the the train should go to cambridge and should should ...
{ "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": "MUL0972", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004067
train
audio
multi_turn
[ { "role": "user", "text": "good day. how are you.", "turn_id": 1 }, { "role": "assistant", "text": "okay, thank you. i'd like to book a hotel. a three star hotel in the opposite side of cambridge south in cheap price range.", "turn_id": 2 }, { "role": "user", "text": "ok, can...
{ "chunk_text": "Chunk 1: good day. how are you.\nChunk 2: okay, thank you. i'd like to book a hotel. a three star hotel in the opposite side of cambridge south in cheap price range.\nChunk 3: ok, can you please submit one inexpensive. price range.", "dialogue_text": "Chunk 1: good day. how are you.\nChunk 2: okay,...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "good day. how are you.", "role": "user", "streaming_reasoning": "The user mentions Good day. how are you. It is not yet clear whether the user needs the full scope of th...
{ "answer": "I can help book that. Could you provide the hotel_type, day, stay_length?", "reasoning": "Across the dialogue, the user is wanting to book hotel. Key context: how are you; okay, thank you; i'd like to book a hotel; a three star hotel in the opposite side of cambridge south in cheap price range. The ans...
{ "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": "MUL0854", "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_004068
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm good. how are you.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train that goes to stevens.", "turn_id": 3 }, { "role": "assistant", "text": "um departing...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm good. how are you.\nChunk 3: i'm looking for a train that goes to stevens.\nChunk 4: um departing from cambridge.\nChunk 5: um, uh, let's i want to live on the day before sunday to sunday, sorry.\nChunk 6: if it can arrive. at stevens, an hour after 2.", "dialogue_text...
{ "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 find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train that goes to stevens. Key context: how are you; i'm looking for a train that goes to stevens; um departing from cambridge; um, uh, let's i want to live on the day before sund...
{ "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": "SNG0355", "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_004069
train
audio
multi_turn
[ { "role": "user", "text": "hello, good morning.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i'm looking for a train.", "turn_id": 2 }, { "role": "user", "text": "the. i'd like to go to norwich. the train should arrive by 8 45.", "turn_id": 3 }, { "role":...
{ "chunk_text": "Chunk 1: hello, good morning.\nChunk 2: hi, i'm looking for a train.\nChunk 3: the. i'd like to go to norwich. the train should arrive by 8 45.\nChunk 4: the train should leave on tuesday.\nChunk 5: and to depart. from the legendary university.\nChunk 6: anything arriving by 8 45.\nChunk 7: um can i ...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello, good morning.", "role": "user", "streaming_reasoning": "The user mentions Hello, good morning. It is not yet clear whether the user needs the full scope of the us...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for train. Key context: hello, good morning; hi, i'm looking for a train; i'd like to go to norwich; the train should arrive by 8 45. The answer shoul...
{ "category": "education", "subcategory": "course_planning", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3011", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004070
train
audio
multi_turn
[ { "role": "user", "text": "yes, yes, you are, right.", "turn_id": 1 }, { "role": "assistant", "text": "uh, okay, that sounds great. and i want to book a table for 8 people sorry for me and seven friends.", "turn_id": 2 }, { "role": "user", "text": "yes, yes, you're right.", ...
{ "chunk_text": "Chunk 1: yes, yes, you are, right.\nChunk 2: uh, okay, that sounds great. and i want to book a table for 8 people sorry for me and seven friends.\nChunk 3: yes, yes, you're right.\nChunk 4: uh, and i want to book the table at 7:45 p. and on the day before monday.\nChunk 5: uh, yes, yes.\nChunk 6: uh,...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, yes, you are, right.", "role": "user", "streaming_reasoning": "The user mentions Yes, yes, you are, right. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for train. Key context: yes, yes, you are, right; uh, okay, that sounds great; and i want to book a table for 8 people sorry for me and seven friends; yes, yes, you're ...
{ "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": "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_004071
train
audio
multi_turn
[ { "role": "user", "text": "i am good. thanks. i am working. it took the cambridge is a will you be able to assist me.", "turn_id": 1 }, { "role": "assistant", "text": "okay so i'm looking for something some kind of an attraction in town like some kind of a museum or something to go to do", ...
{ "chunk_text": "Chunk 1: i am good. thanks. i am working. it took the cambridge is a will you be able to assist me.\nChunk 2: okay so i'm looking for something some kind of an attraction in town like some kind of a museum or something to go to do\nChunk 3: you have a new recommendation\nChunk 4: uh huh. oh, that sou...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i am good. thanks. i am working. it took the cambridge is a will you be able to assist me.", "role": "user", "streaming_reasoning": "The user mentions I am good. It is n...
{ "answer": "Sure. I can provide the address, phone, area for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for something some kind of an attraction in town like some kind of a museum. Key context: i am working; it took the cambridge is a will you be able to assist me; o...
{ "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": "MUL0884", "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_004072
train
audio
multi_turn
[ { "role": "user", "text": "hello is the customer service of cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i'm looking for some information in cambridge.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello is the customer service of cambridge.\nChunk 2: yes, i'm looking for some information in cambridge.", "dialogue_text": "Chunk 1: hello is the customer service of cambridge.\nChunk 2: yes, i'm looking for some information in cambridge.", "instruction": "Help the user complete a spok...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello is the customer service of cambridge.", "role": "user", "streaming_reasoning": "The user mentions Hello is the customer service of cambridge. It is not yet clear w...
{ "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: hello is the customer service of cambridge; yes, i'm looking for some information in cambridge. The answer should focus on the latest user turn while i...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1147", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_004073
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.", "dialogue_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 li...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user discusses \"hello.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user discusses \"hell...
{ "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": "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_004074
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes i'm planning a trip to cambridge and i was looking for information on a particular place it's called the a and b guest house", "turn_id": 2 }, { "role": "user", "text": "uh could yo...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: yes i'm planning a trip to cambridge and i was looking for information on a particular place it's called the a and b guest house\nChunk 3: uh could you tell me what kind of star hotel it is\nChunk 4: uh, do they have internet. and could i also get their phone number, ...
{ "num_checkpoints": 4, "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": "Sure. I can provide the stars, internet, phone for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for information on a particular place it's called the a. Key context: and could i also get their phone number, please. The answer should focus on the latest user turn...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL4005", "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_004075
train
audio
multi_turn
[ { "role": "user", "text": "ah yes, i want to book. a 20s for 8 people.", "turn_id": 1 }, { "role": "assistant", "text": "uh, yes, my id number is 4 5 2 3.", "turn_id": 2 }, { "role": "user", "text": "uh, and 4 9 9.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: ah yes, i want to book. a 20s for 8 people.\nChunk 2: uh, yes, my id number is 4 5 2 3.\nChunk 3: uh, and 4 9 9.\nChunk 4: and then 8 6, 3.\nChunk 5: and 0 8 2.\nChunk 6: and 0 4.\nChunk 7: yes, i'm sure.\nChunk 8: okay, thank you. and also i'm looking for a place to stay.", "dialogue_text...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "ah yes, i want to book. a 20s for 8 people.", "role": "user", "streaming_reasoning": "The user mentions Ah yes, i want to book. a 20s for 8 people. It is not yet clear w...
{ "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: ah yes, i want to book; a 20s for 8 people; uh, yes, my id number is 4 5 2 3; uh, and 4 9 9. The answer should focus on the latest user turn...
{ "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": "MUL0393", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }