id
large_stringlengths
23
28
split
large_stringclasses
1 value
modality
large_stringclasses
1 value
turn_type
large_stringclasses
1 value
dialogue
listlengths
1
8
input
dict
streaming
dict
target
dict
taxonomy
dict
quality
dict
source
dict
metadata
dict
audio_multidialog_v02_000965
train
audio
multi_turn
[ { "role": "user", "text": "Human: Do they have an official name, or are you referencing the nickname Tall Blacks?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yeah I am not too sure but that is certainly what they are called", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: Human: Do they have an official name, or are you referencing the nickname Tall Blacks?\nChunk 2: Assistant: Yeah I am not too sure but that is certainly what they are called\nChunk 3: Human: Apparently the Supreme Court enjoys a game of basketball too. On the top floor of the building they s...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Do they have an official name, or are you referencing the nickname Tall Blacks?", "role": "user", "streaming_reasoning": "The user mentions talking about Human, T...
{ "answer": "Good for them, how handy to play there at work.", "reasoning": "Across the dialogue, the user is asking for help with human: apparently the supreme court enjoys a game of basketball too. Key context: Human: Do they have an official name, or are you referencing the nickname Tall Blacks; Assistant: Yeah ...
{ "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_f6789857-c30c-423a-bdf5-d6207dc7db9d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003323
train
audio
multi_turn
[ { "role": "user", "text": "on the.", "turn_id": 1 }, { "role": "assistant", "text": "add up the dot com.", "turn_id": 2 }, { "role": "user", "text": "alright, thank you. uh, i'm also i would also like to book a restaurant that sell famous food. in the city center.", "turn...
{ "chunk_text": "Chunk 1: on the.\nChunk 2: add up the dot com.\nChunk 3: alright, thank you. uh, i'm also i would also like to book a restaurant that sell famous food. in the city center.\nChunk 4: what about the one that is in the food.\nChunk 5: i would like to book for four people at five fifteen p m on sundays.\...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "on the.", "role": "user", "streaming_reasoning": "The user mentions On the. It is not yet clear whether the user needs the full scope of the user's request. The assistan...
{ "answer": "I can help book that. Could you provide the departure, destination?", "reasoning": "Across the dialogue, the user is wanting to book restaurant that sell famous food. Key context: add up the dot com; alright, thank you; uh, i'm also i would also like to book a restaurant that sell famous food; in the c...
{ "category": "finance_consumer", "subcategory": "budget_planning", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1961", "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_000116
train
audio
multi_turn
[ { "role": "user", "text": "The behaviourist who attempts to make psychology a record of behaviour has to trust his memory in making the record.", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: The behaviourist who attempts to make psychology a record of behaviour has to trust his memory in making the record.", "dialogue_text": "Chunk 1: The behaviourist who attempts to make psychology a record of behaviour has to trust his memory in making the record.", "instruction": "Help th...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "The behaviourist who attempts to make psychology a record of behaviour has to trust his memory in making the record.", "role": "user", "streaming_reasoning": "The user m...
{ "answer": "Indeed, just as athletes rely on muscle memory and repetitive practice to perfect their skills, a behaviourist must rely on the accuracy and reliability of their memory to accurately document behavior patterns.", "reasoning": "Across the dialogue, the user discusses \"The behaviourist who attempts to m...
{ "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": "SD-Eval", "dialogue_id": "8230-279154-0006-gym", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003324
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.\nChunk 4: yes, it's marcella coon...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help book that. 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_003325
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "am i to do typical savers.", "turn_id": 2 }, { "role": "user", "text": "and stephanie rodriguez.", "turn_id": 3 }, { "role": "assistant", "text": "i am looking for a par...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: am i to do typical savers.\nChunk 3: and stephanie rodriguez.\nChunk 4: i am looking for a particular. uh, the name is 11 ton house.\nChunk 5: yes.\nChunk 6: uh, the phone number and the price range.\nChunk 7: it.\nChunk 8: mm.", "dialogue_text": "Chunk 1: hello. he...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "Sure. I can provide the pricerange, phone for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for particular. Key context: am i to do typical savers; and stephanie rodriguez; i am looking for a particular; uh, the name is 11 ton house. The answer should focus on th...
{ "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": "MUL2892", "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_003326
train
audio
multi_turn
[ { "role": "user", "text": "0 5 9.", "turn_id": 1 }, { "role": "assistant", "text": "1 6 1 7 9.", "turn_id": 2 }, { "role": "user", "text": "perfect. i'm also looking to book a particular restaurant.", "turn_id": 3 }, { "role": "assistant", "text": "it's called...
{ "chunk_text": "Chunk 1: 0 5 9.\nChunk 2: 1 6 1 7 9.\nChunk 3: perfect. i'm also looking to book a particular restaurant.\nChunk 4: it's called tandoori palace.\nChunk 5: yes, i would like to book for five people.\nChunk 6: for 1430, please.\nChunk 7: yes, it would be on the wednesday.\nChunk 8: my name is shirley. ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "0 5 9.", "role": "user", "streaming_reasoning": "The user mentions 0 5 9. 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 wanting to book particular restaurant. Key context: i'm also looking to book a particular restaurant; it's called tandoori palace; yes, i would like to book for five people; for 1430, please....
{ "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": "MUL3126", "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_003327
train
audio
multi_turn
[ { "role": "user", "text": "are you. how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm all thank you. i need a base to stay cambridge.", "turn_id": 2 }, { "role": "user", "text": "uh, one that's not a hot on.", "turn_id": 3 }, { "role": "assistant"...
{ "chunk_text": "Chunk 1: are you. how are you.\nChunk 2: i'm all thank you. i need a base to stay cambridge.\nChunk 3: uh, one that's not a hot on.\nChunk 4: okay, i needed to have um to not charge me for parking.\nChunk 5: okay. does it offer free wifi.\nChunk 6: i'd like to make a booking for wednesday for three n...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "are you. how are you.", "role": "user", "streaming_reasoning": "The user mentions Are you. how are you. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help book that. Could you provide the area, price?", "reasoning": "Across the dialogue, the user is wanting to book base to stay cambridge. Key context: how are you; i'm all thank you; i need a base to stay cambridge; uh, one that's not a hot on. The answer should focus on the latest user turn wh...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2629", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003328
train
audio
multi_turn
[ { "role": "user", "text": "hi, the customer service.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for a place to stay in cambridge.", "turn_id": 2 }, { "role": "user", "text": "um i want to stay in a small, cheap hotel which has a three star rating.", "tu...
{ "chunk_text": "Chunk 1: hi, the customer service.\nChunk 2: i'm looking for a place to stay in cambridge.\nChunk 3: um i want to stay in a small, cheap hotel which has a three star rating.\nChunk 4: yes, you are correct.\nChunk 5: um yeah, for the price i wanted to be in the moderate price range and. i also need an...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, the customer service.", "role": "user", "streaming_reasoning": "The user mentions Hi, the customer service. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help find a matching hotel option with those details.", "reasoning": "Across the dialogue, the user is searching for place to stay in cambridge. Key context: hi, the customer service; i'm looking for a place to stay in cambridge; um i want to stay in a small, cheap hotel which has a three star ra...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0812", "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_003329
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "how are you.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "the train should be on friday. i'm sorry on...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: how are you.\nChunk 3: i'm looking for a train.\nChunk 4: the train should be on friday. i'm sorry on sunday.\nChunk 5: and should arrive preferably, um i have an event at half past one. so.\nChunk 6: a few minutes earlier.\nChunk 7: and it should depart from london liverpoo...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train. Key context: how are you; i'm looking for a train; the train should be on friday; i'm sorry on sunday. The answer should focus on the latest user turn while incorporating re...
{ "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": "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_multidialog_v02_000966
train
audio
multi_turn
[ { "role": "user", "text": "Human: I guess it's one of those rules people don't know about since no one has done it. Another rule people likely don't know is that cheerleaders for the Saints aren", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: ya I don't like how they aren't allo...
{ "chunk_text": "Chunk 1: Human: I guess it's one of those rules people don't know about since no one has done it. Another rule people likely don't know is that cheerleaders for the Saints aren\nChunk 2: Assistant: ya I don't like how they aren't allowed to eat with players, that seems like an outtdated rule and also...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I guess it's one of those rules people don't know about since no one has done it. Another rule people likely don't know is that cheerleaders for the Saints aren", "role...
{ "answer": "ya they definitely stretch taht over 2 hours sometimes, did you know the avg earnings of an engineer is more than that of an nfl playier?", "reasoning": "Across the dialogue, the user is asking for help with human: i guess it's one of those rules people don't know about since no one has done it. Key co...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_68769b96-2795-4295-a12b-773fbf323c1d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003330
train
audio
multi_turn
[ { "role": "user", "text": "thank you so much.", "turn_id": 1 }, { "role": "assistant", "text": "yes, it's just right.", "turn_id": 2 }, { "role": "user", "text": "uh, j for jelly follows o s e p h.", "turn_id": 3 }, { "role": "assistant", "text": "and w. r i. ...
{ "chunk_text": "Chunk 1: thank you so much.\nChunk 2: yes, it's just right.\nChunk 3: uh, j for jelly follows o s e p h.\nChunk 4: and w. r i. and g g is for game and then follows ht.\nChunk 5: sure, for a email address, j w, both in capital.\nChunk 6: an r i j t.\nChunk 7: uh. okay, edm p.\nChunk 8: at yahoo dot co...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "thank you so much.", "role": "user", "streaming_reasoning": "The user mentions Thank you so much. It is not yet clear whether the user needs the full scope of the user's...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is talking about thank you so much. Key context: thank you so much; yes, it's just right; uh, j for jelly follows o s e p h; and g g is for game and then follows ht. The answer should focus on the latest use...
{ "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": "MUL1724", "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_003331
train
audio
multi_turn
[ { "role": "user", "text": "the phone number in the bosco.", "turn_id": 1 }, { "role": "assistant", "text": "no, can thank you for that.", "turn_id": 2 }, { "role": "user", "text": "alright, thank you for that.", "turn_id": 3 }, { "role": "assistant", "text": "...
{ "chunk_text": "Chunk 1: the phone number in the bosco.\nChunk 2: no, can thank you for that.\nChunk 3: alright, thank you for that.\nChunk 4: yes, manners you can also find in this book for me. text me to commit between the two places.\nChunk 5: i would like to leave the place for transaction by 1830.\nChunk 6: oka...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "the phone number in the bosco.", "role": "user", "streaming_reasoning": "The user mentions The phone number in the bosco. It is not yet clear whether the user needs the ...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for for me. Key context: the phone number in the bosco; no, can thank you for that; alright, thank you for that; yes, manners you can also find in thi...
{ "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": "MUL1532", "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_000117
train
audio
multi_turn
[ { "role": "user", "text": "Will you tell me why?", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: Will you tell me why?", "dialogue_text": "Chunk 1: Will you tell me why?", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chunks.", "length_bucket": "short", "num_turns": 1, "total_transcript_token_count": 7, "u...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Will you tell me why?", "role": "user", "streaming_reasoning": "The user mentions Will you tell me why?. It is not yet clear whether the user needs what specific help th...
{ "answer": "I'm really sorry that you're feeling this way. I can certainly try to explain, but I need a bit more information to understand what you're asking about.", "reasoning": "Across the dialogue, the user discusses \"Will you tell me why?\" over 1 turns. The answer should respond to the latest user turn natu...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "easy", "intent_type": "explain_cause" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SD-Eval", "dialogue_id": "W024_sad_level3_003", "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_003332
train
audio
multi_turn
[ { "role": "user", "text": "i'm looking for a restaurant that falls within the expensive residence and should be the sign of the time.", "turn_id": 1 }, { "role": "assistant", "text": "uh, i would love for the food to yourself. mega mega is possible.", "turn_id": 2 }, { "role": "u...
{ "chunk_text": "Chunk 1: i'm looking for a restaurant that falls within the expensive residence and should be the sign of the time.\nChunk 2: uh, i would love for the food to yourself. mega mega is possible.\nChunk 3: uh, kindly find for me a restaurant that serves indian food.\nChunk 4: yes, my mouse.\nChunk 5: uh,...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm looking for a restaurant that falls within the expensive residence and should be the sign of the time.", "role": "user", "streaming_reasoning": "The user mentions I'...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for restaurant that falls within the expensive residence. Key context: i'm looking for a restaurant that falls within the expensive residence and shou...
{ "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": "MUL2737", "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_003333
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi i'm looking for a train i'm going from uh cambridge to bishop stortford and i want to leave on wednesday and arrive by 9 30 pm", "turn_id": 2 }, { "role": "user", "text": "okay, great. um f...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi i'm looking for a train i'm going from uh cambridge to bishop stortford and i want to leave on wednesday and arrive by 9 30 pm\nChunk 3: okay, great. um for the last arriving train, can i get the departure time travel time as well as the train id.\nChunk 4: okay, thank yo...
{ "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 i'm going from uh cambridge to bishop stortford. Key context: hi i'm looking for a train i'm going from uh cambridge to bishop stortford and...
{ "category": "information_extraction", "subcategory": "pros_cons_extraction", "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": "MUL3243", "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_003334
train
audio
multi_turn
[ { "role": "user", "text": "i need to go to london king's cross, please.", "turn_id": 1 }, { "role": "assistant", "text": "i was traveling for cambridge.", "turn_id": 2 }, { "role": "user", "text": "i have to give unsettling.", "turn_id": 3 }, { "role": "assistant"...
{ "chunk_text": "Chunk 1: i need to go to london king's cross, please.\nChunk 2: i was traveling for cambridge.\nChunk 3: i have to give unsettling.\nChunk 4: and later in evening, please.\nChunk 5: no, that's the opportunity.\nChunk 6: um you can leave after 7 o'clock, that'll be.\nChunk 7: thank you. similar weight...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i need to go to london king's cross, please.", "role": "user", "streaming_reasoning": "The user mentions I need to go to london king's cross, please. It is not yet clear...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is talking about to go to london king's cross. Key context: i need to go to london king's cross, please; i was traveling for cambridge; i have to give unsettling; and later in evening, please. The ...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0050", "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_003335
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i'm good. thanks to you.", "turn_id": 2 }, { "role": "user", "text": "i am looking for a train.", "turn_id": 3 }, { "role": "assistant", "text": "i trained to depart from givin...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i'm good. thanks to you.\nChunk 3: i am looking for a train.\nChunk 4: i trained to depart from giving us going to cambridge and should leave on sunday and should arrive in cambridge by caught up with 10\nChunk 5: in the morning\nChunk 6: yes, please.\nChunk 7: mizuno elite ...
{ "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 arriveby for the matching train option.", "reasoning": "Across the dialogue, the user is searching for train. Key context: thanks to you; i am looking for a train; i trained to depart from giving us going to cambridge and should leave on sunday and should arrive in cambridge by ...
{ "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": "MUL1443", "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_003336
train
audio
multi_turn
[ { "role": "user", "text": "uh, my name is diane.", "turn_id": 1 }, { "role": "assistant", "text": "okay. is d i a n e.", "turn_id": 2 }, { "role": "user", "text": "and then l double e.", "turn_id": 3 }, { "role": "assistant", "text": "um why do you need my ema...
{ "chunk_text": "Chunk 1: uh, my name is diane.\nChunk 2: okay. is d i a n e.\nChunk 3: and then l double e.\nChunk 4: um why do you need my email address.\nChunk 5: um but sorry. i don't prefer to give out my email address.\nChunk 6: um yes, i'm also looking for a place to go in cambridge.\nChunk 7: uh, yes, i would...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, my name is diane.", "role": "user", "streaming_reasoning": "The user mentions Uh, my name is diane. It is not yet clear whether the user needs the full scope of the ...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for place to go in cambridge. Key context: uh, my name is diane; is d i a n e; and then l double e; um why do you need my email address. The answer should focus on the latest user...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "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": "MUL1905", "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_000967
train
audio
multi_turn
[ { "role": "user", "text": "Human: Wow, that amazing, I love horses and was raised on a farm. I learned to ride them when I was small.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Me too. To this day I still find them fascinating!", "turn_id": 2 }, { "role": "user"...
{ "chunk_text": "Chunk 1: Human: Wow, that amazing, I love horses and was raised on a farm. I learned to ride them when I was small.\nChunk 2: Assistant: Me too. To this day I still find them fascinating!\nChunk 3: Human: Yes I do, I don't like when horses are being raced for years and If they don't win races, they p...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Wow, that amazing, I love horses and was raised on a farm. I learned to ride them when I was small.", "role": "user", "streaming_reasoning": "The user mentions ta...
{ "answer": "I do and I agree. I don't like to see them whipped either.", "reasoning": "Across the dialogue, the user is searching for human: wow, that amazing, i love horses and was raised on a farm. Key context: Human: Wow, that amazing, I love horses and was raised on a farm; I learned to ride them when I was sm...
{ "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": "MultiDialog", "dialogue_id": "t_3ae864fd-2d45-4b35-a265-aa73bf3bd445", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003337
train
audio
multi_turn
[ { "role": "user", "text": "i don't give up my mail address.", "turn_id": 1 }, { "role": "assistant", "text": "um i'm looking for a place to stay. should include.", "turn_id": 2 }, { "role": "user", "text": "uh, a place where i can stow. uh, mica and.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: i don't give up my mail address.\nChunk 2: um i'm looking for a place to stay. should include.\nChunk 3: uh, a place where i can stow. uh, mica and.\nChunk 4: it should be in an expensive price range.\nChunk 5: beef. yeah.\nChunk 6: uh, in. it should include free wifi.\nChunk 7: okay.\nChunk...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i don't give up my mail address.", "role": "user", "streaming_reasoning": "The user mentions I don't give up my mail address. It is not yet clear whether the user needs ...
{ "answer": "I can help with the hotel. Could you share the area, hotel_type?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: i don't give up my mail address; um i'm looking for a place to stay; should include; uh, a place where i can stow. The answer should focus on the l...
{ "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": "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_003338
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, sure, please. i'm looking for a place to go in town. can you help me.", "turn_id": 2 }, { "role": "user", "text": "okay, i like to find a filter.", "turn_id": 3 }, { "role": "...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, sure, please. i'm looking for a place to go in town. can you help me.\nChunk 3: okay, i like to find a filter.\nChunk 4: i'd like to go to the center of the town.\nChunk 5: okay. can you recommend anyone.\nChunk 6: okay, it sounds good. can you tell me the phone number ...
{ "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 phone for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: yes, sure, please; i'm looking for a place to go in town; can you help me; okay, i like to find a filter. The answer should focus on the lat...
{ "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": "MUL1239", "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_003339
train
audio
multi_turn
[ { "role": "user", "text": "um yes, please. i'm also looking for a restaurant.", "turn_id": 1 }, { "role": "assistant", "text": "the restaurant should be in a cheap price range and should be in the west of cambridge.", "turn_id": 2 }, { "role": "user", "text": "yes, please. ca...
{ "chunk_text": "Chunk 1: um yes, please. i'm also looking for a restaurant.\nChunk 2: the restaurant should be in a cheap price range and should be in the west of cambridge.\nChunk 3: yes, please. can i just get the address, phone number and post code post code to the missing fog.\nChunk 4: mmhmm.\nChunk 5: great, t...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um yes, please. i'm also looking for a restaurant.", "role": "user", "streaming_reasoning": "The user mentions Um yes, please. i'm also looking for a restaurant. It is n...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for restaurant. Key context: um yes, please; i'm also looking for a restaurant; the restaurant should be in a cheap price range and should be in the west of cambridge; ...
{ "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": "MUL3562", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003340
train
audio
multi_turn
[ { "role": "user", "text": "er.", "turn_id": 1 }, { "role": "assistant", "text": "re z.", "turn_id": 2 }, { "role": "user", "text": "yup.", "turn_id": 3 }, { "role": "assistant", "text": "oh, i see. um, how about from monday.", "turn_id": 4 }, { "ro...
{ "chunk_text": "Chunk 1: er.\nChunk 2: re z.\nChunk 3: yup.\nChunk 4: oh, i see. um, how about from monday.\nChunk 5: okay, great. uh, i also looking for a restaurant that should be in a cheap price range and serving thai food.\nChunk 6: mm. okay. maybe i would like to have some dumplings and steam buns instead.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "er.", "role": "user", "streaming_reasoning": "The user mentions Er. It is not yet clear whether the user needs the full scope of the user's request. The assistant should...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for restaurant that should be in a cheap price range. Key context: um, how about from monday; okay, great; uh, i also looking for a restaurant that sh...
{ "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": "MUL3225", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003341
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 }, { "role": "assista...
{ "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.\nChunk 4: yes, i'm planning going to cambridge.\nChunk 5: yes, and the train should arrive by. 18 o'clock.", "dialogue_text": "Chunk 1: hello, i need some help.\nCh...
{ "num_checkpoints": 5, "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?", "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; yes, i'm planning going to cambridge. The answer should focus...
{ "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_003342
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.", "dialogue_text": "Chunk 1: hello. is t...
{ "num_checkpoints": 4, "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 with the restaurant. Could you share the area?", "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 ser...
{ "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": "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_multidialog_v02_000968
train
audio
multi_turn
[ { "role": "user", "text": "Human: True. Do you know that Baker Mayfield from University of Oklahoma considered quitting football?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I don't blame him. It's a dangerous sport.", "turn_id": 2 }, { "role": "user", "text"...
{ "chunk_text": "Chunk 1: Human: True. Do you know that Baker Mayfield from University of Oklahoma considered quitting football?\nChunk 2: Assistant: I don't blame him. It's a dangerous sport.\nChunk 3: Human: He wanted to pursue competitive gaming instead. He was very good at playing halo 3.", "dialogue_text": "Ch...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: True. Do you know that Baker Mayfield from University of Oklahoma considered quitting football?", "role": "user", "streaming_reasoning": "The user mentions talkin...
{ "answer": "You can get paid to do that?", "reasoning": "Across the dialogue, the user discusses \"True. Do you know that Baker Mayfield from University of.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialo...
{ "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_6ba478d0-f870-4121-96d5-5b7aa4632843", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003343
train
audio
multi_turn
[ { "role": "user", "text": "i was staying from penn state to. till tuesday.", "turn_id": 1 }, { "role": "assistant", "text": "it's for. myself, my wife and three kids.", "turn_id": 2 }, { "role": "user", "text": "ya.", "turn_id": 3 }, { "role": "assistant", "te...
{ "chunk_text": "Chunk 1: i was staying from penn state to. till tuesday.\nChunk 2: it's for. myself, my wife and three kids.\nChunk 3: ya.\nChunk 4: ya. okay.\nChunk 5: okay.\nChunk 6: okay.\nChunk 7: okay.\nChunk 8: yes, it is.", "dialogue_text": "Chunk 1: i was staying from penn state to. till tuesday.\nChunk 2:...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i was staying from penn state to. till tuesday.", "role": "user", "streaming_reasoning": "The user mentions I was staying from penn state to. till tuesday. It is not yet...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is talking about i was staying from penn state to. Key context: i was staying from penn state to; till tuesday; myself, my wife and three kids. The answer should focus on the latest use...
{ "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": "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_003344
train
audio
multi_turn
[ { "role": "user", "text": "hi, i was looking for information in cambridge. there's a particular restaurant. i've heard it's really good. the taj tandoori, do you haven't.", "turn_id": 1 }, { "role": "assistant", "text": "so wonderful. what area is it in.", "turn_id": 2 }, { "role...
{ "chunk_text": "Chunk 1: hi, i was looking for information in cambridge. there's a particular restaurant. i've heard it's really good. the taj tandoori, do you haven't.\nChunk 2: so wonderful. what area is it in.\nChunk 3: thank you in the food type.\nChunk 4: super and the price range.\nChunk 5: thank you and i'm a...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, i was looking for information in cambridge. there's a particular restaurant. i've heard it's really good. the taj tandoori, do you haven't.", "role": "user", "stream...
{ "answer": "Sure. I can provide the arriveby for the matching train option.", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: hi, i was looking for information in cambridge; there's a particular restaurant; i've heard it's really good; the taj tandoori, do you ha...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "hard", "intent_type": "conversational_understanding" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2325", "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_003345
train
audio
multi_turn
[ { "role": "user", "text": "yes. um my phone number should be. mm. 6 1 2 1.", "turn_id": 1 }, { "role": "assistant", "text": "1 0 7 2.", "turn_id": 2 }, { "role": "user", "text": "2, 1.", "turn_id": 3 }, { "role": "assistant", "text": "hmm, no, thanks.", "t...
{ "chunk_text": "Chunk 1: yes. um my phone number should be. mm. 6 1 2 1.\nChunk 2: 1 0 7 2.\nChunk 3: 2, 1.\nChunk 4: hmm, no, thanks.\nChunk 5: no thanks. i don't need that.\nChunk 6: yes, i need a post code. could you please tell me.\nChunk 7: okay, got it.\nChunk 8: mm. i think that's all thank you very much.", ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes. um my phone number should be. mm. 6 1 2 1.", "role": "user", "streaming_reasoning": "The user mentions Yes. um my phone number should be. mm. 6 1 2 1. It is not yet...
{ "answer": "Sure. I can help with the postcode; first I need to identify the right restaurant option.", "reasoning": "Across the dialogue, the user is talking about that. Key context: um my phone number should be; hmm, no, thanks; i don't need that; yes, i need a post code. The answer should focus on the latest us...
{ "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": "SNG0057", "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_003346
train
audio
multi_turn
[ { "role": "user", "text": "hello. is this customer service.", "turn_id": 1 }, { "role": "assistant", "text": "ah can you help me.", "turn_id": 2 }, { "role": "user", "text": "i need some information.", "turn_id": 3 }, { "role": "assistant", "text": "uh, i'm pl...
{ "chunk_text": "Chunk 1: hello. is this customer service.\nChunk 2: ah can you help me.\nChunk 3: i need some information.\nChunk 4: uh, i'm planning my trip around cambridge.\nChunk 5: and i want to find a place to go in.\nChunk 6: yes. uh, i want the attraction to. a type of concert hall.", "dialogue_text": "Chu...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. is this customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello. is this customer service. It is not yet clear whether the user needs ...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for information. Key context: is this customer service; ah can you help me; i need some information; uh, i'm planning my trip around cambridge. 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": "MUL1744", "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_003347
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i find things for yourself.", "turn_id": 2 }, { "role": "user", "text": "i am looking for information in cambridge.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i find things for yourself.\nChunk 3: i am looking for information in cambridge.", "dialogue_text": "Chunk 1: hello.\nChunk 2: i find things for yourself.\nChunk 3: i am looking for information in cambridge.", "instruction": "Help the user complete a spoken task-oriented...
{ "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 is searching for information in cambridge. Key context: i find things for yourself; i am looking for information in cambridge. The answer should focus on the latest user turn while incorporating relevant con...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3575", "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_003348
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "i like a recommendation for a hotel in the east of the city, please. something like a guesthouse.", "turn_id": 2 }, { "role": "user", "text": "so i'm looking something in the model pricing, wh...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: i like a recommendation for a hotel in the east of the city, please. something like a guesthouse.\nChunk 3: so i'm looking something in the model pricing, which includes free wifi.\nChunk 4: that sounds perfect please can you make a booking for me to 6 people that's myself a...
{ "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 wanting to book i like a recommendation for a hotel in the east of the city, please. Key context: i like a recommendation for a hotel in the east of the city, p...
{ "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": "MUL1306", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003349
train
audio
multi_turn
[ { "role": "user", "text": "mm. okay. can i have the first one.", "turn_id": 1 }, { "role": "assistant", "text": "uh, what's the entrance fee.", "turn_id": 2 }, { "role": "user", "text": "okay, so i also looking for a hotel. let's call the cambridge belfry.", "turn_id": 3 ...
{ "chunk_text": "Chunk 1: mm. okay. can i have the first one.\nChunk 2: uh, what's the entrance fee.\nChunk 3: okay, so i also looking for a hotel. let's call the cambridge belfry.\nChunk 4: alright, i would like to book for five people for. wednesday to friday night.\nChunk 5: ya, that's right.\nChunk 6: my name is ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "mm. okay. can i have the first one.", "role": "user", "streaming_reasoning": "The user mentions Mm. okay. can i have the first one. It is not yet clear whether the user ...
{ "answer": "I can help book that. Could you provide the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for hotel. Key context: can i have the first one; uh, what's the entrance fee; okay, so i also looking for a hotel; let's call the cambridge belfry. The answer should focus on...
{ "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": "MUL3213", "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_000969
train
audio
multi_turn
[ { "role": "user", "text": "Human: Would you be interested in the mars colonization project planned for 2023? I guess it will be a reality tv show.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: it would be cool, I did not know plants like Lichen could live there already.", ...
{ "chunk_text": "Chunk 1: Human: Would you be interested in the mars colonization project planned for 2023? I guess it will be a reality tv show.\nChunk 2: Assistant: it would be cool, I did not know plants like Lichen could live there already.\nChunk 3: Human: Yeah I think it sounds cool as well. It would take 2 or ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Would you be interested in the mars colonization project planned for 2023? I guess it will be a reality tv show.", "role": "user", "streaming_reasoning": "The use...
{ "answer": "it seems long", "reasoning": "Across the dialogue, the user discusses \"Would you be interested in the mars colonization project.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Across the dialogue, the user d...
{ "category": "work_productivity", "subcategory": "meeting_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_7ee0c4a5-4910-4731-9ad4-ccb9674f35a6", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003350
train
audio
multi_turn
[ { "role": "user", "text": "3 9 6 0.", "turn_id": 1 }, { "role": "assistant", "text": "6, 4, 3, 3.", "turn_id": 2 }, { "role": "user", "text": "3, 6, 4, 5.", "turn_id": 3 }, { "role": "assistant", "text": "thank you so much for that i'm also looking for somewhe...
{ "chunk_text": "Chunk 1: 3 9 6 0.\nChunk 2: 6, 4, 3, 3.\nChunk 3: 3, 6, 4, 5.\nChunk 4: thank you so much for that i'm also looking for somewhere i can stay in cambridge that should include free wifi have a three star\nChunk 5: rating and in the moderate price range\nChunk 6: okay. could you please book me into that...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "3 9 6 0.", "role": "user", "streaming_reasoning": "The user mentions 3 9 6 0. It is not yet clear whether the user needs the full scope of the user's request. The assist...
{ "answer": "I can help book that. Could you provide the area, hotel_type, party_size?", "reasoning": "Across the dialogue, the user is searching for me into that hotel to stay for two nights starting from thursday. Key context: thank you so much for that i'm also looking for somewhere i can stay in cambridge that ...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2879", "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_003351
train
audio
multi_turn
[ { "role": "user", "text": "hi, i'm looking to get some information. i'm looking for a vietnamese restaurant near downtown cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "oh, okay. is there anything with perchance, english food or like a british pub.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hi, i'm looking to get some information. i'm looking for a vietnamese restaurant near downtown cambridge.\nChunk 2: oh, okay. is there anything with perchance, english food or like a british pub.", "dialogue_text": "Chunk 1: hi, i'm looking to get some information. i'm looking for a vietna...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, i'm looking to get some information. i'm looking for a vietnamese restaurant near downtown cambridge.", "role": "user", "streaming_reasoning": "The user mentions sea...
{ "answer": "I can help with the restaurant. Could you share the price?", "reasoning": "Across the dialogue, the user is searching for vietnamese restaurant near downtown cambridge. Key context: hi, i'm looking to get some information; i'm looking for a vietnamese restaurant near downtown cambridge; is there anythi...
{ "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": "MUL2323", "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_003352
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi, yes, i'm looking for a museum in the center of town. can you help me, please.", "turn_id": 2 }, { "role": "user", "text": "so what's the open hours for the scott polo polo museum, please."...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi, yes, i'm looking for a museum in the center of town. can you help me, please.\nChunk 3: so what's the open hours for the scott polo polo museum, please.", "dialogue_text": "Chunk 1: hello.\nChunk 2: hi, yes, i'm looking for a museum in the center of town. can you help ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help with the attraction. Could you share the area, type?", "reasoning": "Across the dialogue, the user is searching for museum in the center of town. Key context: hi, yes, i'm looking for a museum in the center of town; can you help me, please; so what's the open hours for the scott polo polo mu...
{ "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": "SNG1106", "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_003353
train
audio
multi_turn
[ { "role": "user", "text": "yes, i'm calling from keng lim, so i'm looking for information in cambridge.", "turn_id": 1 }, { "role": "assistant", "text": "mm. yes, i'm looking for a trend.", "turn_id": 2 }, { "role": "user", "text": "well, i will depart from where i am.", ...
{ "chunk_text": "Chunk 1: yes, i'm calling from keng lim, so i'm looking for information in cambridge.\nChunk 2: mm. yes, i'm looking for a trend.\nChunk 3: well, i will depart from where i am.\nChunk 4: it should be cambridge.\nChunk 5: mm, i will leave all these fans. uh, on tomorrow. i will leave tomorrow.\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, i'm calling from keng lim, so i'm looking for information in cambridge.", "role": "user", "streaming_reasoning": "The user mentions Yes, i'm calling from keng lim, ...
{ "answer": "I can help with the train. Could you share the day?", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: yes, i'm calling from keng lim, so i'm looking for information in cambridge; yes, i'm looking for a trend; well, i will depart from where i am; it sh...
{ "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": "MUL0139", "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_003354
train
audio
multi_turn
[ { "role": "user", "text": "sure, jessie j ew f.", "turn_id": 1 }, { "role": "assistant", "text": "i. e. jesse.", "turn_id": 2 }, { "role": "user", "text": "anthony simmons. f i tz.", "turn_id": 3 }, { "role": "assistant", "text": "s i double m.", "turn_id"...
{ "chunk_text": "Chunk 1: sure, jessie j ew f.\nChunk 2: i. e. jesse.\nChunk 3: anthony simmons. f i tz.\nChunk 4: s i double m.\nChunk 5: o nf.\nChunk 6: no, that will be fine. thank you. i am over actually looking for a train going to cambridge departing elite.\nChunk 7: the change should be depending on the same d...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "sure, jessie j ew f.", "role": "user", "streaming_reasoning": "The user mentions Sure, jessie j ew f. It is not yet clear whether the user needs the full scope of the us...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train going to cambridge departing elite. Key context: sure, jessie j ew f; anthony simmons; s i double m; no, that will be fine. The answer should focus on the latest user turn wh...
{ "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": "MUL1455", "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_003355
train
audio
multi_turn
[ { "role": "user", "text": "i want to look for places to go in town.", "turn_id": 1 }, { "role": "assistant", "text": "yes. yes, i'm traveling.", "turn_id": 2 }, { "role": "user", "text": "yes, i prefer the type of multiple sports. thank you.", "turn_id": 3 }, { "r...
{ "chunk_text": "Chunk 1: i want to look for places to go in town.\nChunk 2: yes. yes, i'm traveling.\nChunk 3: yes, i prefer the type of multiple sports. thank you.\nChunk 4: yes. and about the place it's better in the south.\nChunk 5: okay, i will wait.\nChunk 6: yes, the south is better.\nChunk 7: okay. thank you....
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i want to look for places to go in town.", "role": "user", "streaming_reasoning": "The user mentions I want to look for places to go in town. It is not yet clear whether...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is talking about to look for places to go in town. Key context: i want to look for places to go in town; yes, i'm traveling; yes, i prefer the type of multiple sports; and about the place it's...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3917", "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_003356
train
audio
multi_turn
[ { "role": "user", "text": "and yes, and the the train should arrive by 1745.", "turn_id": 1 }, { "role": "assistant", "text": "yes. and the issue depart from cambridge.", "turn_id": 2 }, { "role": "user", "text": "yes, and should go to brookstone.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: and yes, and the the train should arrive by 1745.\nChunk 2: yes. and the issue depart from cambridge.\nChunk 3: yes, and should go to brookstone.\nChunk 4: yes. uh, yes, uh, that's right.\nChunk 5: ok, i will wait.\nChunk 6: okay, i will choose it.\nChunk 7: i want to make a booking.\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and yes, and the the train should arrive by 1745.", "role": "user", "streaming_reasoning": "The user mentions And yes, and the the train should arrive by 1745. It is not...
{ "answer": "I can help book that. Could you provide the day?", "reasoning": "Across the dialogue, the user is wanting to book to make a booking. Key context: and yes, and the the train should arrive by 1745; and the issue depart from cambridge; yes, and should go to brookstone; uh, yes, uh, that's right. The answe...
{ "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": "MUL3895", "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_003357
train
audio
multi_turn
[ { "role": "user", "text": "well, i suppose it should be in the moderate price range and the. may i know. do you have any recommendation.", "turn_id": 1 }, { "role": "assistant", "text": "hmm. well, that's okay.", "turn_id": 2 }, { "role": "user", "text": "mm. i. i prefer the ...
{ "chunk_text": "Chunk 1: well, i suppose it should be in the moderate price range and the. may i know. do you have any recommendation.\nChunk 2: hmm. well, that's okay.\nChunk 3: mm. i. i prefer the fifth one.\nChunk 4: no thanks. but may i know the phone number of the restaurant.\nChunk 5: um thank you so much.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "well, i suppose it should be in the moderate price range and the. may i know. do you have any recommendation.", "role": "user", "streaming_reasoning": "The user mentions...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is asking for recommendations about that. Key context: well, i suppose it should be in the moderate price range and the; do you have any recommendation; well, that's okay; i prefer the fifth one. ...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "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_multidialog_v02_000970
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yea that would be amazing to get to see. Have you ever tried to play the piano?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Yes a little bit, I have one but I am a bass player. Did you know about the piano that Freddie Mercury used to play b...
{ "chunk_text": "Chunk 1: Human: Yea that would be amazing to get to see. Have you ever tried to play the piano?\nChunk 2: Assistant: Yes a little bit, I have one but I am a bass player. Did you know about the piano that Freddie Mercury used to play bohemian rhapsody?\nChunk 3: Human: No, what about it?", "dialogue...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yea that would be amazing to get to see. Have you ever tried to play the piano?", "role": "user", "streaming_reasoning": "The user mentions talking about Human, H...
{ "answer": "That is the same piano that was used by Paul Mc Cartney to play hey Jude!!", "reasoning": "Across the dialogue, the user discusses \"Yea that would be amazing to get to see. Have you ever.\" over 3 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone."...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_ca614fc6-030d-43aa-bf66-647cd83aeb0b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000971
train
audio
multi_turn
[ { "role": "user", "text": "Human: I did - I wasn't even a huge fan of the commercials which is normally my favorite part", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I thought they were just ok too. Who were you rooting for?", "turn_id": 2 }, { "role": "user", ...
{ "chunk_text": "Chunk 1: Human: I did - I wasn't even a huge fan of the commercials which is normally my favorite part\nChunk 2: Assistant: I thought they were just ok too. Who were you rooting for?\nChunk 3: Human: Anyone but the Patriots lol - so Rams last night. Normally I am more of a MN person", "dialogue_tex...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I did - I wasn't even a huge fan of the commercials which is normally my favorite part", "role": "user", "streaming_reasoning": "The user mentions talking about H...
{ "answer": "Uh oh... I am from Chicago so we have an NFC North friction. Just kidding, we are united by our hatred of Green Bay!", "reasoning": "Across the dialogue, the user discusses \"I did - I wasn't even a huge fan of the commercials which.\" over 3 turns. The answer should respond to the latest user turn nat...
{ "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_ade77e20-2dbc-4c28-ab04-25bca9924ba3", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000972
train
audio
multi_turn
[ { "role": "user", "text": "Human: The fear of snakes is hard-wired not only in human brains but also in monkey brains. Were you ever afraid of your corn snake?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: No, I've never been afraid of snakes -- I mean, I'm afraid of them inte...
{ "chunk_text": "Chunk 1: Human: The fear of snakes is hard-wired not only in human brains but also in monkey brains. Were you ever afraid of your corn snake?\nChunk 2: Assistant: No, I've never been afraid of snakes -- I mean, I'm afraid of them intellectually if I know they're venomous, but I enjoy handling them. A...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: The fear of snakes is hard-wired not only in human brains but also in monkey brains. Were you ever afraid of your corn snake?", "role": "user", "streaming_reasoni...
{ "answer": "I don't think I've ever seen a venomous one, except at zoos and the like. I see a lot of black snakes and grass snakes here, and they're handy for keeping down rodents that bother my garden.", "reasoning": "The dialogue is about \"The fear of snakes is hard-wired not only in human brains.\" The user la...
{ "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_6e37ba37-8e95-4ab4-9f5c-7f42be81df36", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003358
train
audio
multi_turn
[ { "role": "user", "text": "to customer service.", "turn_id": 1 }, { "role": "assistant", "text": "i would like to book a taxi.", "turn_id": 2 }, { "role": "user", "text": "uh, but i would like to departure from. downing college.", "turn_id": 3 } ]
{ "chunk_text": "Chunk 1: to customer service.\nChunk 2: i would like to book a taxi.\nChunk 3: uh, but i would like to departure from. downing college.", "dialogue_text": "Chunk 1: to customer service.\nChunk 2: i would like to book a taxi.\nChunk 3: uh, but i would like to departure from. downing college.", "in...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "to customer service.", "role": "user", "streaming_reasoning": "The user mentions To customer service. It is not yet clear whether the user needs the full scope of the us...
{ "answer": "I can help book that. Could you provide the destination, time?", "reasoning": "Across the dialogue, the user is wanting to book taxi. Key context: to customer service; i would like to book a taxi; uh, but i would like to departure from; downing college. The answer should focus on the latest user turn w...
{ "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": "SNG0110", "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_003359
train
audio
multi_turn
[ { "role": "user", "text": "that's right. thank you.", "turn_id": 1 }, { "role": "assistant", "text": "actually, on 1245.", "turn_id": 2 }, { "role": "user", "text": "thank you so much.", "turn_id": 3 }, { "role": "assistant", "text": "the 1145.", "turn_id"...
{ "chunk_text": "Chunk 1: that's right. thank you.\nChunk 2: actually, on 1245.\nChunk 3: thank you so much.\nChunk 4: the 1145.\nChunk 5: yes, is adult or hallway.\nChunk 6: e d u a r offering do.\nChunk 7: h o l l l for letter o w a y.\nChunk 8: thank you so much.", "dialogue_text": "Chunk 1: that's right. thank ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "that's right. thank you.", "role": "user", "streaming_reasoning": "The user mentions That's right. thank you. 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 that's right. Key context: that's right; actually, on 1245; thank you so much; yes, is adult or hallway. The answer should focus on the latest user turn while incorporat...
{ "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": "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_multidialog_v02_000973
train
audio
multi_turn
[ { "role": "user", "text": "Human: I heard there's chips in the footballs and shoulder pads to keep track of speed and all the stats the diehard fans care about. It's pretty cool how that works", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: that is cool, hopefully they dont use ...
{ "chunk_text": "Chunk 1: Human: I heard there's chips in the footballs and shoulder pads to keep track of speed and all the stats the diehard fans care about. It's pretty cool how that works\nChunk 2: Assistant: that is cool, hopefully they dont use those on the Saints cheerleaders, that would be creepy!\nChunk 3: H...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I heard there's chips in the footballs and shoulder pads to keep track of speed and all the stats the diehard fans care about. It's pretty cool how that works", "role":...
{ "answer": "ya that is weird, I wonder if that hurts or helps them, I think that would make me play better haha", "reasoning": "Across the dialogue, the user is asking for help with human: i heard there's chips in the footballs and shoulder pads to keep track of speed and all the stats the diehard fans care about....
{ "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_68769b96-2795-4295-a12b-773fbf323c1d", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003360
train
audio
multi_turn
[ { "role": "user", "text": "thank you so much. i'll wait.", "turn_id": 1 }, { "role": "assistant", "text": "hi, yes, i'm here in this.", "turn_id": 2 }, { "role": "user", "text": "a great word, okay.", "turn_id": 3 }, { "role": "assistant", "text": "i think the...
{ "chunk_text": "Chunk 1: thank you so much. i'll wait.\nChunk 2: hi, yes, i'm here in this.\nChunk 3: a great word, okay.\nChunk 4: i think they'll be a bit too late.\nChunk 5: that might work. but just to make is there any earlier.\nChunk 6: i have to rush and i can't do that with my finger.\nChunk 7: yes, that mea...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "thank you so much. i'll wait.", "role": "user", "streaming_reasoning": "The user mentions Thank you so much. i'll wait. It is not yet clear whether the user needs the fu...
{ "answer": "I can help. What task or place should I focus on?", "reasoning": "Across the dialogue, the user is talking about thank you so much. Key context: thank you so much; hi, yes, i'm here in this; a great word, okay; i think they'll be a bit too late. The answer should focus on the latest user turn while inc...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0051", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000974
train
audio
multi_turn
[ { "role": "user", "text": "Human: Thats really weird! I definitely wouldn't want my bones to be hollow! That makes sense though, they have to be light enough to fly.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: So true! I was shocked to learn that there in Australia there are...
{ "chunk_text": "Chunk 1: Human: Thats really weird! I definitely wouldn't want my bones to be hollow! That makes sense though, they have to be light enough to fly.\nChunk 2: Assistant: So true! I was shocked to learn that there in Australia there are wild birds that can mimic the sound of chainsaws and car alarms. H...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Thats really weird! I definitely wouldn't want my bones to be hollow! That makes sense though, they have to be light enough to fly.", "role": "user", "streaming_r...
{ "answer": "I'm not sure of their name, but they put a bird that can say, \"Polly want a cracker?\" to shame! No sleep, at all? There's no way, I could make that migration.", "reasoning": "Across the dialogue, the user is asking for help with my bones to be hollow. Key context: Human: Thats really weird; I definit...
{ "category": "tech_support", "subcategory": "device_troubleshooting", "difficulty": "hard", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_0529b8e5-7049-40c4-95e0-eff5eb341876", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000118
train
audio
multi_turn
[ { "role": "user", "text": "How does the stock market work?", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: How does the stock market work?", "dialogue_text": "Chunk 1: How does the stock market work?", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chunks.", "length_bucket": "short", "num_turns": 1, "total_transcript_t...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "How does the stock market work?", "role": "user", "streaming_reasoning": "The user mentions How does the stock market work?. It is not yet clear whether the user needs w...
{ "answer": "The stock market is like a big store where people buy and sell pieces of companies. Imagine if you could buy a piece of your favorite toy store!", "reasoning": "Across the dialogue, the user discusses \"How does the stock market.\" over 1 turns. The answer should respond to the latest user turn natural...
{ "category": "finance_consumer", "subcategory": "budget_planning", "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": "105_1", "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_003361
train
audio
multi_turn
[ { "role": "user", "text": "yes, ma'am, i'm looking for a particular restaurant, please.", "turn_id": 1 }, { "role": "assistant", "text": "its name is called pizza hard city center.", "turn_id": 2 }, { "role": "user", "text": "yes, i want to book a table for one. at 15 hours o...
{ "chunk_text": "Chunk 1: yes, ma'am, i'm looking for a particular restaurant, please.\nChunk 2: its name is called pizza hard city center.\nChunk 3: yes, i want to book a table for one. at 15 hours on wednesday.\nChunk 4: okay. uh, how about 12 hours then.\nChunk 5: yes, my name is gerald russia.\nChunk 6: is ca.\nC...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, ma'am, i'm looking for a particular restaurant, please.", "role": "user", "streaming_reasoning": "The user mentions Yes, ma'am, i'm looking for a particular restaur...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is searching for particular restaurant. Key context: yes, ma'am, i'm looking for a particular restaurant, please; its name is called pizza hard city center; yes, i want to book a table for one; ...
{ "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": "SNG1583", "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_003362
train
audio
multi_turn
[ { "role": "user", "text": "i.", "turn_id": 1 }, { "role": "assistant", "text": "i am looking for information in cambridge.", "turn_id": 2 }, { "role": "user", "text": "i'm looking for a train that is leaving off the. 15 minutes before 3. and it should be one of friday.", ...
{ "chunk_text": "Chunk 1: i.\nChunk 2: i am looking for information in cambridge.\nChunk 3: i'm looking for a train that is leaving off the. 15 minutes before 3. and it should be one of friday.\nChunk 4: it should. go to the same place as the way i'm inquiring for information and it should depart from london king's c...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i.", "role": "user", "streaming_reasoning": "The user mentions I. It is not yet clear whether the user needs the full scope of the user's request. The assistant should a...
{ "answer": "Sure. I can provide the travel_time, arriveby for the matching train option.", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: i am looking for information in cambridge; i'm looking for a train that is leaving off the; 15 minutes before 3; and it shou...
{ "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": "MUL2582", "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_003363
train
audio
multi_turn
[ { "role": "user", "text": "i also want to book a taxi to convenient between two places.", "turn_id": 1 }, { "role": "assistant", "text": "hmm, should i should arrive by the book.", "turn_id": 2 }, { "role": "user", "text": "may i know the phone number of the taxi.", "turn...
{ "chunk_text": "Chunk 1: i also want to book a taxi to convenient between two places.\nChunk 2: hmm, should i should arrive by the book.\nChunk 3: may i know the phone number of the taxi.\nChunk 4: god, thank you so much.\nChunk 5: sure. um, my phone number. 6 8 1 2.\nChunk 6: 5, 2, 5, 7.\nChunk 7: 2, 0.\nChunk 8: u...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i also want to book a taxi to convenient between two places.", "role": "user", "streaming_reasoning": "The user mentions I also want to book a taxi to convenient between...
{ "answer": "Sure. I can help with the phone; first I need to identify the right taxi option.", "reasoning": "Across the dialogue, the user is wanting to book taxi to convenient between two places. Key context: i also want to book a taxi to convenient between two places; hmm, should i should arrive by the book; may...
{ "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": "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_spokenwoz_v02_003364
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i'm looking for a place to stay. um, i would like to find the expensive guesthouse that has free wifi.", "turn_id": 2 }, { "role": "user", "text": "how about something that's in the modera...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi, i'm looking for a place to stay. um, i would like to find the expensive guesthouse that has free wifi.\nChunk 3: how about something that's in the moderate price range.\nChunk 4: okay. uh, could you let me know what the first one is.\nChunk 5: okay. uh, can i get the add...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "Sure. I can provide the stars, phone for the matching hotel option.", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: hi, i'm looking for a place to stay; um, i would like to find the expensive guesthouse that has free wifi; how about something that's in the mod...
{ "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": "MUL2444", "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_003365
train
audio
multi_turn
[ { "role": "user", "text": "yes, my name is leonard jacobs. le o. nar d is the first name. the last name is joc bs. m. a..", "turn_id": 1 }, { "role": "assistant", "text": "i don't want to give up my email.", "turn_id": 2 }, { "role": "user", "text": "i'm also looking for more...
{ "chunk_text": "Chunk 1: yes, my name is leonard jacobs. le o. nar d is the first name. the last name is joc bs. m. a..\nChunk 2: i don't want to give up my email.\nChunk 3: i'm also looking for more information.\nChunk 4: a place to say.\nChunk 5: it should be a hotel.\nChunk 6: it should include free parking.\nChu...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, my name is leonard jacobs. le o. nar d is the first name. the last name is joc bs. m. a..", "role": "user", "streaming_reasoning": "The user mentions Yes, my name i...
{ "answer": "I can help with the hotel. Could you share the area, price?", "reasoning": "Across the dialogue, the user is searching for more information. Key context: yes, my name is leonard jacobs; nar d is the first name; the last name is joc bs; i don't want to give up my email. The answer should focus on the la...
{ "category": "work_productivity", "subcategory": "meeting_summary", "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": "MUL3365", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000975
train
audio
multi_turn
[ { "role": "user", "text": "Human: I would love to watch such a crazy match as well. It is crazy how soccer makes more money than football, basketball, and golf combined.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Do you like to swim? could you swim with your limbs bound as ...
{ "chunk_text": "Chunk 1: Human: I would love to watch such a crazy match as well. It is crazy how soccer makes more money than football, basketball, and golf combined.\nChunk 2: Assistant: Do you like to swim? could you swim with your limbs bound as a dolphin? I couldn't I am sure.\nChunk 3: Human: I could swim like...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I would love to watch such a crazy match as well. It is crazy how soccer makes more money than football, basketball, and golf combined.", "role": "user", "streami...
{ "answer": "hahahahahaahah, is amazing what the German Soccer player did, to pay for surgeries for 23 children in Brazil", "reasoning": "Across the dialogue, the user discusses \"I would love to watch such a crazy match as well. It is.\" over 3 turns. The answer should respond to the latest user turn naturally, ma...
{ "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_8f8b5454-ad49-4fa5-8753-976cefe7f590", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_sdeval_v02_000119
train
audio
multi_turn
[ { "role": "user", "text": "Will you tell me why?", "turn_id": 1 } ]
{ "chunk_text": "Chunk 1: Will you tell me why?", "dialogue_text": "Chunk 1: Will you tell me why?", "instruction": "Help the user complete a spoken task-oriented dialogue based on gradually revealed audio/transcript chunks.", "length_bucket": "short", "num_turns": 1, "total_transcript_token_count": 7, "u...
{ "num_checkpoints": 1, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Will you tell me why?", "role": "user", "streaming_reasoning": "The user mentions Will you tell me why?. It is not yet clear whether the user needs what specific help th...
{ "answer": "I'm really sorry that you're feeling upset, but I'd be happy to explain if you give me a moment. Let's try to work through this together and find a solution.", "reasoning": "Across the dialogue, the user discusses \"Will you tell me why?\" over 1 turns. The answer should respond to the latest user turn...
{ "category": "information_extraction", "subcategory": "long_note_to_summary", "difficulty": "easy", "intent_type": "explain_cause" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SD-Eval", "dialogue_id": "M022_angry_level3_003", "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_003366
train
audio
multi_turn
[ { "role": "user", "text": "hi, my name is james. i need your help with the phone number.", "turn_id": 1 }, { "role": "assistant", "text": "um i need to contact a specialist department in the hospital.", "turn_id": 2 }, { "role": "user", "text": "um it's a brain federal depart...
{ "chunk_text": "Chunk 1: hi, my name is james. i need your help with the phone number.\nChunk 2: um i need to contact a specialist department in the hospital.\nChunk 3: um it's a brain federal department.", "dialogue_text": "Chunk 1: hi, my name is james. i need your help with the phone number.\nChunk 2: um i need...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hi, my name is james. i need your help with the phone number.", "role": "user", "streaming_reasoning": "The user mentions Hi, my name is james. It is not yet clear wheth...
{ "answer": "I can help find a matching hospital option with those details.", "reasoning": "Across the dialogue, the user is talking about your help with the phone number. Key context: hi, my name is james; i need your help with the phone number; um i need to contact a specialist department in the hospital; um it's...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "task_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0574", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003367
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i am planning a trip to cambridge and i need some information, please.", "turn_id": 2 }, { "role": "user", "text": "so 1st of all, i am looking for a train plane.", "turn_id": 3 }, ...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes, i am planning a trip to cambridge and i need some information, please.\nChunk 3: so 1st of all, i am looking for a train plane.\nChunk 4: birmingham new street.\nChunk 5: uh, it should go through to cambridge, please.\nChunk 6: i'd like to travel on wednesday, please.\n...
{ "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 find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for train plane. Key context: yes, i am planning a trip to cambridge and i need some information, please; so 1st of all, i am looking for a train plane; birmingham new street; uh, it s...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2030", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003368
train
audio
multi_turn
[ { "role": "user", "text": "yes, that sounds wonderful. all i really need right now is the post code, please.", "turn_id": 1 }, { "role": "assistant", "text": "great, thank you.", "turn_id": 2 }, { "role": "user", "text": "yes, i'm also looking for a train. and i like the trai...
{ "chunk_text": "Chunk 1: yes, that sounds wonderful. all i really need right now is the post code, please.\nChunk 2: great, thank you.\nChunk 3: yes, i'm also looking for a train. and i like the train leaving on wednesday, so in five days time.\nChunk 4: on the 19th and i have a meeting at 9 am and need to be there ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, that sounds wonderful. all i really need right now is the post code, please.", "role": "user", "streaming_reasoning": "The user mentions Yes, that sounds wonderful....
{ "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, that sounds wonderful; all i really need right now is the post code, please; great, thank you; yes, i'm also looking for ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL3420", "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_003369
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi, i'm looking for a restaurant that serves food like yorkshire pudding and shepherd's pie. something in the expensive price range in the city center.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: hello.\nChunk 2: hi, i'm looking for a restaurant that serves food like yorkshire pudding and shepherd's pie. something in the expensive price range in the city center.", "dialogue_text": "Chunk 1: hello.\nChunk 2: hi, i'm looking for a restaurant that serves food like yorkshire pudding an...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for restaurant that serves food like yorkshire pudding. Key context: hi, i'm looking for a restaurant that serves food like yorkshire pudding and shepherd's pie; something in the ...
{ "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": "MUL3256", "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_003370
train
audio
multi_turn
[ { "role": "user", "text": "uh, yes, please book it for me just for the same group of people as the restaurant. for a five nights starting from. monday, please.", "turn_id": 1 }, { "role": "assistant", "text": "1 0 1 7 6 7.", "turn_id": 2 }, { "role": "user", "text": "hello.",...
{ "chunk_text": "Chunk 1: uh, yes, please book it for me just for the same group of people as the restaurant. for a five nights starting from. monday, please.\nChunk 2: 1 0 1 7 6 7.\nChunk 3: hello.\nChunk 4: yes, sure. please book a table for me and we have six people. and we would like to have. our lunch at 15:30 o...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, yes, please book it for me just for the same group of people as the restaurant. for a five nights starting from. monday, please.", "role": "user", "streaming_reasoni...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user is searching for it for me just for the same group of people as the restaurant. Key context: uh, yes, please book it for me just for the same group of people as the restaurant; for a fi...
{ "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": "MUL0228", "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_003371
train
audio
multi_turn
[ { "role": "user", "text": "yes, i'm looking for a place to dine and. i'm in the north part of the city. we would like to try some european food.", "turn_id": 1 }, { "role": "assistant", "text": "uh, yes, please book it for me just for the same group of people as the restaurant. for a five ni...
{ "chunk_text": "Chunk 1: yes, i'm looking for a place to dine and. i'm in the north part of the city. we would like to try some european food.\nChunk 2: uh, yes, please book it for me just for the same group of people as the restaurant. for a five nights starting from. monday, please.\nChunk 3: 1 0 1 7 6 7.\nChunk 4...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, i'm looking for a place to dine and. i'm in the north part of the city. we would like to try some european food.", "role": "user", "streaming_reasoning": "The user ...
{ "answer": "I can help book that. Could you provide the area, food, price?", "reasoning": "Across the dialogue, the user is searching for place to dine and. Key context: yes, i'm looking for a place to dine and; i'm in the north part of the city; we would like to try some european food; uh, yes, please book it for...
{ "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": "MUL0228", "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_003372
train
audio
multi_turn
[ { "role": "user", "text": "okay. uh, could you let me know what the first one is.", "turn_id": 1 }, { "role": "assistant", "text": "okay. uh, can i get the address the star rating of the hotel and also the phone number.", "turn_id": 2 }, { "role": "user", "text": "okay. um, t...
{ "chunk_text": "Chunk 1: okay. uh, could you let me know what the first one is.\nChunk 2: okay. uh, can i get the address the star rating of the hotel and also the phone number.\nChunk 3: okay. um, thanks for that. and i'm also looking for a attraction in the middle of the city.\nChunk 4: yes.\nChunk 5: um okay, wha...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. uh, could you let me know what the first one is.", "role": "user", "streaming_reasoning": "The user mentions Okay. uh, could you let me know what the first one is....
{ "answer": "Sure. I can provide the phone for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for attraction in the middle of the city. Key context: uh, could you let me know what the first one is; uh, can i get the address the star rating of the hotel and also the phone ...
{ "category": "information_extraction", "subcategory": "constraints_extraction", "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": "MUL2444", "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_003373
train
audio
multi_turn
[ { "role": "user", "text": "who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm telling you what to do. can you help me.", "turn_id": 1 }, { "role": "assistant", "text": "i am looking for a train.", "turn_id": 2 } ]
{ "chunk_text": "Chunk 1: who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm telling you what to do. can you help me.\nChunk 2: i am looking for a train.", "dialogue_text": "Chunk 1: who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm ...
{ "num_checkpoints": 2, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "who. hello, you speaking with philip and i'm looking for some information in cambridge. i'm telling you what to do. can you help me.", "role": "user", "streaming_reasoni...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: hello, you speaking with philip and i'm looking for some information in cambridge; i'm telling you what to do; can you help m...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "information_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0628", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000976
train
audio
multi_turn
[ { "role": "user", "text": "Human: Hi, do you like th NFL?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I do like the NFL. Do you?", "turn_id": 2 }, { "role": "user", "text": "Human: I do. My favorite team is the Chicago Bears. Do you have a favorite?", "tu...
{ "chunk_text": "Chunk 1: Human: Hi, do you like th NFL?\nChunk 2: Assistant: I do like the NFL. Do you?\nChunk 3: Human: I do. My favorite team is the Chicago Bears. Do you have a favorite?", "dialogue_text": "Chunk 1: Human: Hi, do you like th NFL?\nChunk 2: Assistant: I do like the NFL. Do you?\nChunk 3: Human: ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Hi, do you like th NFL?", "role": "user", "streaming_reasoning": "The user mentions Human: Hi, do you like th NFL?. It is not yet clear whether the user needs wha...
{ "answer": "I like the Ravens and the Eagles!", "reasoning": "Across the dialogue, the user discusses \"Hi, do you like th NFL?\" 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 \"Hi,...
{ "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_28560728-a743-4bb4-8ab1-038d71fd13b5", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003374
train
audio
multi_turn
[ { "role": "user", "text": "that's right. 8.", "turn_id": 1 }, { "role": "assistant", "text": "thank you so much.", "turn_id": 2 }, { "role": "user", "text": "wow, that's nice.", "turn_id": 3 }, { "role": "assistant", "text": "sure. may i know the car type.", ...
{ "chunk_text": "Chunk 1: that's right. 8.\nChunk 2: thank you so much.\nChunk 3: wow, that's nice.\nChunk 4: sure. may i know the car type.\nChunk 5: oh, that's nice.\nChunk 6: well, i think that's awful tonight.\nChunk 7: wow, that's kind of you.\nChunk 8: um okay, goodbye.", "dialogue_text": "Chunk 1: that's rig...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "that's right. 8.", "role": "user", "streaming_reasoning": "The user mentions That's right. 8. It is not yet clear whether the user needs the full scope of the user's req...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is asking for recommendations about that's right. Key context: that's right; thank you so much; wow, that's nice; may i know the car type. The answer should focus on the latest user turn while inc...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0001", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003375
train
audio
multi_turn
[ { "role": "user", "text": "good day.", "turn_id": 1 }, { "role": "assistant", "text": "yes. could you please does this mean looking for a place to dine, please.", "turn_id": 2 }, { "role": "user", "text": "yes um it should be um serving um chinese food and should be in the ex...
{ "chunk_text": "Chunk 1: good day.\nChunk 2: yes. could you please does this mean looking for a place to dine, please.\nChunk 3: yes um it should be um serving um chinese food and should be in the expensive price range and also be um um the opposite\nChunk 4: or from the east\nChunk 5: okay. um. could you please loo...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "good day.", "role": "user", "streaming_reasoning": "The user mentions Good day. It is not yet clear whether the user needs the full scope of the user's request. The assi...
{ "answer": "Sure. I can provide the address for the matching restaurant option.", "reasoning": "Across the dialogue, the user is searching for place to dine. Key context: could you please does this mean looking for a place to dine, please; yes um it should be um serving um chinese food and should be in the expensi...
{ "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": "MUL2461", "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_003376
train
audio
multi_turn
[ { "role": "user", "text": "hello with this customer service.", "turn_id": 1 }, { "role": "assistant", "text": "oh, sure. the name of the hotel. bridge guest health.", "turn_id": 2 }, { "role": "user", "text": "thank you very much.", "turn_id": 3 }, { "role": "assi...
{ "chunk_text": "Chunk 1: hello with this customer service.\nChunk 2: oh, sure. the name of the hotel. bridge guest health.\nChunk 3: thank you very much.\nChunk 4: uh, i'm currently traveling in cambridge and i have some.\nChunk 5: uh, yes, i'm trying to find a particular.", "dialogue_text": "Chunk 1: hello with t...
{ "num_checkpoints": 5, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello with this customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello with this customer service. It is not yet clear whether the user need...
{ "answer": "I can help with the hotel. Could you share the area, price, hotel_type?", "reasoning": "Across the dialogue, the user discusses \"hello with this customer.\" over 5 turns. The answer should respond to the latest user turn naturally, maintaining the conversational tone.", "response": "Reasoning: Acros...
{ "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": "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_003377
train
audio
multi_turn
[ { "role": "user", "text": "um thank you so much. so do you have any recommendation of that.", "turn_id": 1 }, { "role": "assistant", "text": "well, may i know.", "turn_id": 2 }, { "role": "user", "text": "well, i prefer the test 1.", "turn_id": 3 }, { "role": "ass...
{ "chunk_text": "Chunk 1: um thank you so much. so do you have any recommendation of that.\nChunk 2: well, may i know.\nChunk 3: well, i prefer the test 1.\nChunk 4: okay. may i know the two options.\nChunk 5: okay. what's the next one.\nChunk 6: okay, that's all.\nChunk 7: wow. i i don't need reservation, but i need...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "um thank you so much. so do you have any recommendation of that.", "role": "user", "streaming_reasoning": "The user mentions Um thank you so much. It is not yet clear wh...
{ "answer": "Sure. I can provide the address for the matching hotel option.", "reasoning": "Across the dialogue, the user is asking for recommendations about reservation. Key context: um thank you so much; so do you have any recommendation of that; well, may i know; well, i prefer the test 1. The answer should focu...
{ "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": "MUL1127", "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_003378
train
audio
multi_turn
[ { "role": "user", "text": "okay, thank you. if you find the train, i would like to make a booking.", "turn_id": 1 }, { "role": "assistant", "text": "yes, of course. my id number is 2 3, 2 0.", "turn_id": 2 }, { "role": "user", "text": "5 5 0 2.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: okay, thank you. if you find the train, i would like to make a booking.\nChunk 2: yes, of course. my id number is 2 3, 2 0.\nChunk 3: 5 5 0 2.\nChunk 4: 3, 2, 0, 8.\nChunk 5: 9 7 4 8.\nChunk 6: yes i'm also looking for a place to go in town and i really want to you know have the thing that w...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, thank you. if you find the train, i would like to make a booking.", "role": "user", "streaming_reasoning": "The user mentions searching for Okay. It is not yet cle...
{ "answer": "I can help find a matching attraction option with those details.", "reasoning": "Across the dialogue, the user is searching for place to go in town. Key context: okay, thank you; if you find the train, i would like to make a booking; yes, of course; my id number is 2 3, 2 0. The answer should focus on ...
{ "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": "MUL0382", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003379
train
audio
multi_turn
[ { "role": "user", "text": "okay. how about saturday.", "turn_id": 1 }, { "role": "assistant", "text": "okay. can you give me for a saturday.", "turn_id": 2 }, { "role": "user", "text": "okay.", "turn_id": 3 }, { "role": "assistant", "text": "yes, i also want t...
{ "chunk_text": "Chunk 1: okay. how about saturday.\nChunk 2: okay. can you give me for a saturday.\nChunk 3: okay.\nChunk 4: yes, i also want to put a taxi to community between the two places.\nChunk 5: it's 4 8 1 7.\nChunk 6: 0 7 7 6.\nChunk 7: and age 3.\nChunk 8: yes, i'll be living in rohit hotel by eight thirty...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay. how about saturday.", "role": "user", "streaming_reasoning": "The user mentions Okay. how about saturday. It is not yet clear whether the user needs the full scope...
{ "answer": "I can help with the taxi. Could you share the destination?", "reasoning": "Across the dialogue, the user is talking about to put a taxi to community between the two places. Key context: how about saturday; can you give me for a saturday; yes, i also want to put a taxi to community between the two place...
{ "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": "MUL2309", "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_003380
train
audio
multi_turn
[ { "role": "user", "text": "yes, the train should depart from cambridge and should go to london liverpool state.", "turn_id": 1 }, { "role": "assistant", "text": "the train should live up to 1045 on sunday.", "turn_id": 2 }, { "role": "user", "text": "yes. uh, can i please get...
{ "chunk_text": "Chunk 1: yes, the train should depart from cambridge and should go to london liverpool state.\nChunk 2: the train should live up to 1045 on sunday.\nChunk 3: yes. uh, can i please get the price.\nChunk 4: £13 and 20. thank you very much, ma'am.\nChunk 5: what about the arrival of time, ma'am.\nChunk ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yes, the train should depart from cambridge and should go to london liverpool state.", "role": "user", "streaming_reasoning": "The user mentions Yes, the train should de...
{ "answer": "I can help with the attraction. Could you share the area?", "reasoning": "Across the dialogue, the user is searching for places to go in town. Key context: yes, the train should depart from cambridge and should go to london liverpool state; the train should live up to 1045 on sunday; uh, can i please g...
{ "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": "MUL2612", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003381
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "um yes, i'm looking for some information in cambridge.", "turn_id": 2 }, { "role": "user", "text": "hmm, i'm looking for.", "turn_id": 3 }, { "role": "assistant", "text": "well...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: um yes, i'm looking for some information in cambridge.\nChunk 3: hmm, i'm looking for.\nChunk 4: well, i have an important meeting in the western part of the city, so i prefer to dine there.\nChunk 5: mm. yes, it matters. so i suppose it should be in the in the cheap price r...
{ "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 find a matching restaurant option with those details.", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: um yes, i'm looking for some information in cambridge; hmm, i'm looking for; well, i have an important meeting in the western part of th...
{ "category": "daily_life", "subcategory": "shopping_decision", "difficulty": "medium", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "SNG0057", "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_003382
train
audio
multi_turn
[ { "role": "user", "text": "and then 3 6, 0, 5.", "turn_id": 1 }, { "role": "assistant", "text": "folio 3 1 do you need to repeat.", "turn_id": 2 }, { "role": "user", "text": "yes, please go ahead.", "turn_id": 3 }, { "role": "assistant", "text": "yes, that's a...
{ "chunk_text": "Chunk 1: and then 3 6, 0, 5.\nChunk 2: folio 3 1 do you need to repeat.\nChunk 3: yes, please go ahead.\nChunk 4: yes, that's all right.\nChunk 5: no, thank you would not.\nChunk 6: thank you very much. could you please just repeat all the deals from you.\nChunk 7: and what is the departure time.\nCh...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and then 3 6, 0, 5.", "role": "user", "streaming_reasoning": "The user mentions And then 3 6, 0, 5. It is not yet clear whether the user needs the full scope of the user...
{ "answer": "Sure. I can provide the leaveat for the matching train option.", "reasoning": "Across the dialogue, the user is wanting to book to repeat. Key context: and then 3 6, 0, 5; folio 3 1 do you need to repeat; yes, please go ahead; yes, that's all right. The answer should focus on the latest user turn while...
{ "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": "SNG0050", "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_003383
train
audio
multi_turn
[ { "role": "user", "text": "yeah.", "turn_id": 1 }, { "role": "assistant", "text": "i'll be going to cambridge and i'd like to beat anytime after 1115.", "turn_id": 2 }, { "role": "user", "text": "yeah. okay, thank you.", "turn_id": 3 }, { "role": "assistant", ...
{ "chunk_text": "Chunk 1: yeah.\nChunk 2: i'll be going to cambridge and i'd like to beat anytime after 1115.\nChunk 3: yeah. okay, thank you.\nChunk 4: is that perfect. and what's the price for this.\nChunk 5: yes.\nChunk 6: okay and tell me something i'm also looking for a recommendation for a hotel it doesn't need...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "yeah.", "role": "user", "streaming_reasoning": "The user mentions Yeah. It is not yet clear whether the user needs the full scope of the user's request. The assistant sh...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is searching for recommendation for a hotel it doesn't need to have free parking uh. Key context: i'll be going to cambridge and i'd like to beat anytime after 1115; okay, thank you...
{ "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": "MUL2688", "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_003384
train
audio
multi_turn
[ { "role": "user", "text": "mm. okay. um just to reconfirm what is the hotel type.", "turn_id": 1 }, { "role": "assistant", "text": "okay, cool. uh, i will make a reservation mine.", "turn_id": 2 }, { "role": "user", "text": "uh, i also want to book a taxi to travel between th...
{ "chunk_text": "Chunk 1: mm. okay. um just to reconfirm what is the hotel type.\nChunk 2: okay, cool. uh, i will make a reservation mine.\nChunk 3: uh, i also want to book a taxi to travel between the restaurant and hotel.\nChunk 4: uh. i want to arrive the restaurant by 2 p m.\nChunk 5: yes, i think that to refer.\...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "mm. okay. um just to reconfirm what is the hotel type.", "role": "user", "streaming_reasoning": "The user mentions Mm. okay. um just to reconfirm what is the hotel type....
{ "answer": "I can help book that. Could you provide the departure, destination?", "reasoning": "Across the dialogue, the user is wanting to book taxi to travel between the restaurant. Key context: um just to reconfirm what is the hotel type; uh, i will make a reservation mine; uh, i also want to book a taxi to tra...
{ "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": "MUL0563", "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_003385
train
audio
multi_turn
[ { "role": "user", "text": "my name is carol. i need a taxi.", "turn_id": 1 }, { "role": "assistant", "text": "i'd like to book a taxi.", "turn_id": 2 }, { "role": "user", "text": "i'm going to read a book.", "turn_id": 3 }, { "role": "assistant", "text": "okay...
{ "chunk_text": "Chunk 1: my name is carol. i need a taxi.\nChunk 2: i'd like to book a taxi.\nChunk 3: i'm going to read a book.\nChunk 4: okay. thank you very much, and i'll be departing from the state.", "dialogue_text": "Chunk 1: my name is carol. i need a taxi.\nChunk 2: i'd like to book a taxi.\nChunk 3: i'm ...
{ "num_checkpoints": 4, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "my name is carol. i need a taxi.", "role": "user", "streaming_reasoning": "The user mentions My name is carol. i need a taxi. It is not yet clear whether the user needs ...
{ "answer": "I can help book that. Could you provide the time?", "reasoning": "Across the dialogue, the user is wanting to book taxi. Key context: my name is carol; i need a taxi; i'd like to book a taxi; i'm going to read a book. The answer should focus on the latest user turn while incorporating relevant context ...
{ "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": "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_multidialog_v02_000977
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah - he was good in it. He's funny.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: He is funny. I liked him in that movie with Sandra Bullock.", "turn_id": 2 }, { "role": "user", "text": "Human: Oh I don't think I have seen th...
{ "chunk_text": "Chunk 1: Human: Yeah - he was good in it. He's funny.\nChunk 2: Assistant: He is funny. I liked him in that movie with Sandra Bullock.\nChunk 3: Human: Oh I don't think I have seen that one.", "dialogue_text": "Chunk 1: Human: Yeah - he was good in it. He's funny.\nChunk 2: Assistant: He is funny. ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah - he was good in it. He's funny.", "role": "user", "streaming_reasoning": "The user mentions Human: Yeah - he was good in it. He's funny. It is not yet clear...
{ "answer": "It's good. I think it's where she's his boss and has him pose as a boyfriend and then end up falling in love. If I'm right, Betty White is in it too.", "reasoning": "Across the dialogue, the user discusses \"Yeah - he was good in it. He's.\" over 3 turns. The answer should respond to the latest user tu...
{ "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_00f2662b-0f83-4e00-b8e5-e731638f3690", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000978
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yea, like when Georgia Tech defeated Cumberland 222-0 for the highest score recorded in a game.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: what was going through the coachs head then? that is a horrible thing to do to another team?", "t...
{ "chunk_text": "Chunk 1: Human: Yea, like when Georgia Tech defeated Cumberland 222-0 for the highest score recorded in a game.\nChunk 2: Assistant: what was going through the coachs head then? that is a horrible thing to do to another team?\nChunk 3: Human: Might not be completely intentional. Happened in a game he...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yea, like when Georgia Tech defeated Cumberland 222-0 for the highest score recorded in a game.", "role": "user", "streaming_reasoning": "The user mentions talkin...
{ "answer": "true, but the coach should put in the third string or something. even the cheerleaders maybe.", "reasoning": "Across the dialogue, the user is asking for help with human: yea, like when georgia tech defeated cumberland 222-0 for the highest score recorded in a game. Key context: Human: Yea, like when G...
{ "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_029f1b38-d6a7-4105-af8b-5e3d58da2971", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000979
train
audio
multi_turn
[ { "role": "user", "text": "Human: After this many years, one would think he would take the hint. Are they really? I never knew that, just like both the Red Sox and Liverpool F.C are owned by the same investment company.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I know that...
{ "chunk_text": "Chunk 1: Human: After this many years, one would think he would take the hint. Are they really? I never knew that, just like both the Red Sox and Liverpool F.C are owned by the same investment company.\nChunk 2: Assistant: I know that the Red Sox are partly owed by the New York Times, the paper of th...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: After this many years, one would think he would take the hint. Are they really? I never knew that, just like both the Red Sox and Liverpool F.C are owned by the same investme...
{ "answer": "I've never been. The Sox have been there since 1912.", "reasoning": "Across the dialogue, the user is asking for help with human: after this many years, one would think he would take the hint. Key context: Human: After this many years, one would think he would take the hint; Are they really; I never kn...
{ "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": "MultiDialog", "dialogue_id": "t_cafe82d2-ca62-4889-8b7c-67cdd712685f", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003386
train
audio
multi_turn
[ { "role": "user", "text": "is that customer service.", "turn_id": 1 }, { "role": "assistant", "text": "i want to look for a train, please help me.", "turn_id": 2 }, { "role": "user", "text": "um the train should live on tuesday.", "turn_id": 3 }, { "role": "assist...
{ "chunk_text": "Chunk 1: is that customer service.\nChunk 2: i want to look for a train, please help me.\nChunk 3: um the train should live on tuesday.\nChunk 4: yes, and should leave after eleven o'clock. quack.\nChunk 5: yes, and this train should go to norwich.\nChunk 6: and should depart from cambridge, please.\...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "is that customer service.", "role": "user", "streaming_reasoning": "The user mentions Is that customer service. It is not yet clear whether the user needs the full scope...
{ "answer": "Sure. I can provide the travel_time, id, ticket for the matching train option.", "reasoning": "Across the dialogue, the user is asking for help with to look for a train. Key context: is that customer service; i want to look for a train, please help me; um the train should live on tuesday; yes, and shou...
{ "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": "MUL3905", "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_003387
train
audio
multi_turn
[ { "role": "user", "text": "hello.", "turn_id": 1 }, { "role": "assistant", "text": "yes i'm looking for some information in cambridge i'm looking for information train um should i'm coming from king's lynn and i'd like to come", "turn_id": 2 }, { "role": "user", "text": "to c...
{ "chunk_text": "Chunk 1: hello.\nChunk 2: yes i'm looking for some information in cambridge i'm looking for information train um should i'm coming from king's lynn and i'd like to come\nChunk 3: to cambridge on sunday and arrive you know just after ten o'clock\nChunk 4: mmhmm.\nChunk 5: yes.\nChunk 6: oh, that sound...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. It is not yet clear whether the user needs the full scope of the user's request. The assistant ...
{ "answer": "I can help find a matching train option with those details.", "reasoning": "Across the dialogue, the user is searching for oh, that sounds good. Key context: oh, that sounds good; yes, just for myself; yes, it is one o nine; four, two, five. The answer should focus on the latest user turn while incorpo...
{ "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": "MUL4028", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003388
train
audio
multi_turn
[ { "role": "user", "text": "is wayne couldn't.", "turn_id": 1 }, { "role": "assistant", "text": "i am lucky for a particular hotel. it is called. uh, egg, egg or guest house.", "turn_id": 2 }, { "role": "user", "text": "yes. yes.", "turn_id": 3 }, { "role": "assist...
{ "chunk_text": "Chunk 1: is wayne couldn't.\nChunk 2: i am lucky for a particular hotel. it is called. uh, egg, egg or guest house.\nChunk 3: yes. yes.\nChunk 4: okay.\nChunk 5: in the area. a phone number and a star of the hotel.\nChunk 6: starve the hotel.\nChunk 7: okay.\nChunk 8: phone number.", "dialogue_text...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "is wayne couldn't.", "role": "user", "streaming_reasoning": "The user mentions Is wayne couldn't. It is not yet clear whether the user needs the full scope of the user's...
{ "answer": "Sure. I can provide the stars, phone for the matching hotel option.", "reasoning": "Across the dialogue, the user is talking about is wayne couldn't. Key context: is wayne couldn't; i am lucky for a particular hotel; it is called; uh, egg, egg or guest house. The answer should focus on the latest user ...
{ "category": "daily_life", "subcategory": "home_task", "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": "SNG1210", "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_000980
train
audio
multi_turn
[ { "role": "user", "text": "Human: Hmmm, I think he won for Lincoln for sure, and There Will Be Blood. The latter movie was really good. I'm not sure about the third one though.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Blazing saddles was nominated 3 times, I honestly have...
{ "chunk_text": "Chunk 1: Human: Hmmm, I think he won for Lincoln for sure, and There Will Be Blood. The latter movie was really good. I'm not sure about the third one though.\nChunk 2: Assistant: Blazing saddles was nominated 3 times, I honestly have no idea what that movie is about. I guess I probably should check ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Hmmm, I think he won for Lincoln for sure, and There Will Be Blood. The latter movie was really good. I'm not sure about the third one though.", "role": "user", "...
{ "answer": "Oh its a comedy, then I definitely want to see it. I love comedy and spoof movies. I also like science fiction.", "reasoning": "Across the dialogue, the user discusses \"Hmmm, I think he won for Lincoln for sure, and There Will.\" over 3 turns. The answer should respond to the latest user turn naturall...
{ "category": "social_communication", "subcategory": "message_reply", "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_96578d43-347b-4936-8603-aff6a3421788", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000981
train
audio
multi_turn
[ { "role": "user", "text": "Human: Do you like reading about superheroes such as black panther?", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I do, Black Panther is one of my favorites, do you like heroes?", "turn_id": 2 }, { "role": "user", "text": "Human: I so...
{ "chunk_text": "Chunk 1: Human: Do you like reading about superheroes such as black panther?\nChunk 2: Assistant: I do, Black Panther is one of my favorites, do you like heroes?\nChunk 3: Human: I sometimes do like browsing through them in comic books.", "dialogue_text": "Chunk 1: Human: Do you like reading about ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Do you like reading about superheroes such as black panther?", "role": "user", "streaming_reasoning": "The user mentions talking about Human. It is not yet clear ...
{ "answer": "There's a lot you miss on the movies, so I like reading the comics, Chadwick Boseman is a great actor", "reasoning": "Across the dialogue, the user is wanting to book human: do you like reading about superheroes such as black panther. Key context: Human: Do you like reading about superheroes such as bl...
{ "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_552a81c8-c15a-4c07-871e-955796f3741b", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000982
train
audio
multi_turn
[ { "role": "user", "text": "Human: I wonder if your school's team is good. I know the highest score in college football ever was 222-0.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: My team, WVU Mountaineers, good or bad get my support and they do well but have ups and downs. I...
{ "chunk_text": "Chunk 1: Human: I wonder if your school's team is good. I know the highest score in college football ever was 222-0.\nChunk 2: Assistant: My team, WVU Mountaineers, good or bad get my support and they do well but have ups and downs. I think it's just the fan support and community support that we all ...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: I wonder if your school's team is good. I know the highest score in college football ever was 222-0.", "role": "user", "streaming_reasoning": "The user mentions a...
{ "answer": "Well that's the competition mentality taken to extreme, so prevalent today, I think at these times we are missing the point really.", "reasoning": "Across the dialogue, the user is asking for help with human: i wonder if your school's team is good. Key context: Human: I wonder if your school's team is ...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "hard", "intent_type": "opinion_sharing" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "MultiDialog", "dialogue_id": "t_4c8e31cb-e68a-46de-b1b3-aade6d735b7f", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003389
train
audio
multi_turn
[ { "role": "user", "text": "hello. have i reached customer service.", "turn_id": 1 }, { "role": "assistant", "text": "i am looking for a place to stay in cambridge.", "turn_id": 2 }, { "role": "user", "text": "it would be a hotel, please.", "turn_id": 3 }, { "role"...
{ "chunk_text": "Chunk 1: hello. have i reached customer service.\nChunk 2: i am looking for a place to stay in cambridge.\nChunk 3: it would be a hotel, please.\nChunk 4: it should include free parking.\nChunk 5: the hotel should be in the west.\nChunk 6: that is all for now.\nChunk 7: yes, i would like to book it f...
{ "num_checkpoints": 7, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. have i reached customer service.", "role": "user", "streaming_reasoning": "The user mentions Hello. have i reached customer service. It is not yet clear whether t...
{ "answer": "You are welcome. I can help again if anything else comes up.", "reasoning": "Across the dialogue, the user is searching for place to stay in cambridge. Key context: have i reached customer service; i am looking for a place to stay in cambridge; it would be a hotel, please; it should include free parkin...
{ "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": "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_000983
train
audio
multi_turn
[ { "role": "user", "text": "Human: Haha yes I think you're right. But I don't like them it's how the Saints treat their cheerleaders, I think that a cheerleader should not have to leave the restaurant if a player is already ther", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: For...
{ "chunk_text": "Chunk 1: Human: Haha yes I think you're right. But I don't like them it's how the Saints treat their cheerleaders, I think that a cheerleader should not have to leave the restaurant if a player is already there, that seems very sexist\nChunk 2: Assistant: For sure, people should be able to go eat whe...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Haha yes I think you're right. But I don't like them it's how the Saints treat their cheerleaders, I think that a cheerleader should not have to leave the restaurant if a pla...
{ "answer": "For sure, that's a ton of organisms. I love dogs too, they are so awesome. Do you have a dog?", "reasoning": "Across the dialogue, the user is asking for help with human: haha yes i think you're right. Key context: Human: Haha yes I think you're right; You a big animal person; Human: yes I love dogs; a...
{ "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_8b672636-2b47-4de2-ac80-bfbcff406835", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003390
train
audio
multi_turn
[ { "role": "user", "text": "uh, is this customer service.", "turn_id": 1 }, { "role": "assistant", "text": "yes, i am planning my trip in cambridge and can you help me to find a train.", "turn_id": 2 }, { "role": "user", "text": "ann, i want to go to cambridge.", "turn_id"...
{ "chunk_text": "Chunk 1: uh, is this customer service.\nChunk 2: yes, i am planning my trip in cambridge and can you help me to find a train.\nChunk 3: ann, i want to go to cambridge.\nChunk 4: uh, i think i will depart from bishop spotlight.\nChunk 5: mm, maybe on wednesday.\nChunk 6: well, i think i will leave aft...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "uh, is this customer service.", "role": "user", "streaming_reasoning": "The user mentions Uh, is this customer service. It is not yet clear whether the user needs the fu...
{ "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 for. Key context: uh, is this customer service; yes, i am planning my trip in cambridge and can you help me to find a train; ann, i want to go to ...
{ "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": "MUL1753", "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_000984
train
audio
multi_turn
[ { "role": "user", "text": "Human: Yeah how would you feel if you were in the losing team? I think I would just laugh it out.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: I would throw my hands up and just think \"well I am here for the education after all\". lol", "turn_i...
{ "chunk_text": "Chunk 1: Human: Yeah how would you feel if you were in the losing team? I think I would just laugh it out.\nChunk 2: Assistant: I would throw my hands up and just think \"well I am here for the education after all\". lol\nChunk 3: Human: I don't think there is anything to learn from that loss, I just...
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Yeah how would you feel if you were in the losing team? I think I would just laugh it out.", "role": "user", "streaming_reasoning": "The user mentions talking abo...
{ "answer": "Yes I agree. Former Patriots RB Benjarvus Green-Ellis has never fumbled the football once during his NFL career. That's pretty impressive!", "reasoning": "Across the dialogue, the user discusses \"Yeah how would you feel if you were in the losing team? I.\" over 3 turns. The answer should respond to th...
{ "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_8a114d55-161d-4573-8d4b-5477afb3e26e", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003391
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 } ]
{ "chunk_text": "Chunk 1: hello, can you hear me.\nChunk 2: is that customer service.\nChunk 3: i'm looking for a train.", "dialogue_text": "Chunk 1: hello, can you hear me.\nChunk 2: is that customer service.\nChunk 3: i'm looking for a train.", "instruction": "Help the user complete a spoken task-oriented dialo...
{ "num_checkpoints": 3, "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 with the train. Could you share the departure, destination, day?", "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. The answer should focus on the latest user turn while incorporating r...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "easy", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "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_003392
train
audio
multi_turn
[ { "role": "user", "text": "hello. hello.", "turn_id": 1 }, { "role": "assistant", "text": "hi there. i'm looking for some information in cambridge, please. i am looking for a train that leaves on tuesday and goes to cambridge.", "turn_id": 2 }, { "role": "user", "text": "i'll...
{ "chunk_text": "Chunk 1: hello. hello.\nChunk 2: hi there. i'm looking for some information in cambridge, please. i am looking for a train that leaves on tuesday and goes to cambridge.\nChunk 3: i'll be departing from kingsland. i'm actually near this in some attractions i'd like to arrive by six fifteen.\nChunk 4: ...
{ "num_checkpoints": 6, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "hello. hello.", "role": "user", "streaming_reasoning": "The user mentions Hello. hello. It is not yet clear whether the user needs the full scope of the user's request. ...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for information in cambridge. Key context: i'm looking for some information in cambridge, please; i am looking for a train that leaves on tuesday and ...
{ "category": "daily_life", "subcategory": "home_task", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL2053", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_multidialog_v02_000985
train
audio
multi_turn
[ { "role": "user", "text": "Human: Free always good! Soldiers use to make radios out of razor blades and pencils in WW2 they dubbed the the foxhole radios.", "turn_id": 1 }, { "role": "assistant", "text": "Assistant: Canadian radios also have to play 40% canadian music.", "turn_id": 2 }...
{ "chunk_text": "Chunk 1: Human: Free always good! Soldiers use to make radios out of razor blades and pencils in WW2 they dubbed the the foxhole radios.\nChunk 2: Assistant: Canadian radios also have to play 40% canadian music.\nChunk 3: Human: I think that's a good ideal. I think it helps to preserve their culture....
{ "num_checkpoints": 3, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "Human: Free always good! Soldiers use to make radios out of razor blades and pencils in WW2 they dubbed the the foxhole radios.", "role": "user", "streaming_reasoning": ...
{ "answer": "I guess, although I do not think that they need that rule. A lot of artists that I listen to are already Canadian and I think that they make excellent music.", "reasoning": "Across the dialogue, the user is wanting to book their culture. Key context: Human: Free always good; Soldiers use to make radios...
{ "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_30adb8cb-1a8f-4108-b80f-7be485de16d5", "language": "en", "license": "cc", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003393
train
audio
multi_turn
[ { "role": "user", "text": "i'm well, and how are you.", "turn_id": 1 }, { "role": "assistant", "text": "i'm looking for a train.", "turn_id": 2 }, { "role": "user", "text": "sure. and which information do you need.", "turn_id": 3 }, { "role": "assistant", "tex...
{ "chunk_text": "Chunk 1: i'm well, and how are you.\nChunk 2: i'm looking for a train.\nChunk 3: sure. and which information do you need.\nChunk 4: so um we'll be leaving eli on wednesday.\nChunk 5: i'm off to a cambridge.\nChunk 6: so i'd like you to arrive by quarter past 8 in the morning.\nChunk 7: i will hold.\n...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "i'm well, and how are you.", "role": "user", "streaming_reasoning": "The user mentions I'm well, and how are you. It is not yet clear whether the user needs the full sco...
{ "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 well, and how are you; i'm looking for a train; and which information do you need; so um we'll be leaving eli on wednesday. The answer should focus on the l...
{ "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": "SNG0877", "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_003394
train
audio
multi_turn
[ { "role": "user", "text": "okay, great then let's just make it in the south.", "turn_id": 1 }, { "role": "assistant", "text": "um please search for me. thank you.", "turn_id": 2 }, { "role": "user", "text": "thank you so much.", "turn_id": 3 }, { "role": "assistan...
{ "chunk_text": "Chunk 1: okay, great then let's just make it in the south.\nChunk 2: um please search for me. thank you.\nChunk 3: thank you so much.\nChunk 4: okay, then i just want to have some fun. any recommendation.\nChunk 5: okay, this sounds great.\nChunk 6: thank you so much.\nChunk 7: okay, lucia. have you ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, great then let's just make it in the south.", "role": "user", "streaming_reasoning": "The user mentions Okay, great then let's just make it in the south. It is not...
{ "answer": "Sure. I can provide the type for the matching attraction option.", "reasoning": "Across the dialogue, the user is searching for to have some fun. Key context: okay, great then let's just make it in the south; um please search for me; thank you so much; okay, then i just want to have some fun. The answe...
{ "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": "MUL1744", "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_003395
train
audio
multi_turn
[ { "role": "user", "text": "and i'm looking for a place to stay.", "turn_id": 1 }, { "role": "assistant", "text": "the hotel shouldn't include any cyberspace and should be in the type of a hotel does also include and cafes parking and should be in", "turn_id": 2 }, { "role": "user...
{ "chunk_text": "Chunk 1: and i'm looking for a place to stay.\nChunk 2: the hotel shouldn't include any cyberspace and should be in the type of a hotel does also include and cafes parking and should be in\nChunk 3: the cheap price\nChunk 4: how about one that has free wifi.\nChunk 5: okay. may you please make a book...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "and i'm looking for a place to stay.", "role": "user", "streaming_reasoning": "The user mentions And i'm looking for a place to stay. It is not yet clear whether the use...
{ "answer": "I can help book that with the details you gave. Would you like me to confirm the reservation?", "reasoning": "Across the dialogue, the user is searching for place to stay. Key context: and i'm looking for a place to stay; the hotel shouldn't include any cyberspace and should be in the type of a hotel d...
{ "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": "MUL2667", "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_003396
train
audio
multi_turn
[ { "role": "user", "text": "mm. i think that's okay.", "turn_id": 1 }, { "role": "assistant", "text": "sure, please make a reservation for us.", "turn_id": 2 }, { "role": "user", "text": "mm. mm, they are my friends and me. um, i have 7 friends.", "turn_id": 3 }, { ...
{ "chunk_text": "Chunk 1: mm. i think that's okay.\nChunk 2: sure, please make a reservation for us.\nChunk 3: mm. mm, they are my friends and me. um, i have 7 friends.\nChunk 4: right, totally for 8 people.\nChunk 5: yes, mining numbers should be. 7 5 2 8.\nChunk 6: 3, 6 double 5.\nChunk 7: 8 7 9 3.\nChunk 8: 8 doub...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "mm. i think that's okay.", "role": "user", "streaming_reasoning": "The user mentions Mm. i think that's okay. It is not yet clear whether the user needs the full scope o...
{ "answer": "I can help with the train. Could you share the departure, destination, day?", "reasoning": "Across the dialogue, the user is wanting to book i think that's okay. Key context: i think that's okay; sure, please make a reservation for us; mm, they are my friends and me; um, i have 7 friends. The answer sh...
{ "category": "social_communication", "subcategory": "message_reply", "difficulty": "medium", "intent_type": "booking_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL0315", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }
audio_spokenwoz_v02_003397
train
audio
multi_turn
[ { "role": "user", "text": "okay, thank you so much. and what's the area of that.", "turn_id": 1 }, { "role": "assistant", "text": "okay, confirmed. well, uh, i think it's offered the hotel hotel information.", "turn_id": 2 }, { "role": "user", "text": "yes, i'm also looking f...
{ "chunk_text": "Chunk 1: okay, thank you so much. and what's the area of that.\nChunk 2: okay, confirmed. well, uh, i think it's offered the hotel hotel information.\nChunk 3: yes, i'm also looking for a trend. the treasure depart from cambridge.\nChunk 4: and it should go to boxroom should arrive by a quarter to 5 ...
{ "num_checkpoints": 8, "turn_checkpoints": [ { "checkpoint_id": "C1", "confidence": "medium", "observed_text": "okay, thank you so much. and what's the area of that.", "role": "user", "streaming_reasoning": "The user mentions Okay, thank you so much. and what's the area of that. I...
{ "answer": "Sure. I can provide the ticket, leaveat for the matching train option.", "reasoning": "Across the dialogue, the user is searching for trend. Key context: okay, thank you so much; and what's the area of that; okay, confirmed; well, uh, i think it's offered the hotel hotel information. The answer should ...
{ "category": "daily_life", "subcategory": "personal_preference", "difficulty": "hard", "intent_type": "search_request" }
{ "audio_quality": "standard", "is_high_quality": true, "natural_reasoning": true, "reasoning_quality": "high", "sft_ready": true, "taxonomy_quality": "high", "timestamp_quality": "standard", "target_grounded": true }
{ "audio_id": null, "dataset": "SpokenWOZ", "dialogue_id": "MUL1139", "language": "en", "license": "cc-by-nc-4.0", "turn_ids": [] }
{ "created_by": "rule_based_pipeline_with_content_grounding", "notes": null, "release_version": "vFinal" }