{"url":"/dataset/candor-corpus-1","name":"CANDOR Corpus","full_name":"CANDOR = Conversation: A Naturalistic Dataset of Online Recordings","description_markdown":"The CANDOR corpus is a large, novel, multimodal corpus of 1,656 recorded conversations in spoken English. This 7+ million word, 850 hour corpus totals over 1TB of audio, video, and transcripts, with moment-to-moment measures of vocal, facial, and semantic expression, along with an extensive survey of speaker post conversation reflections.","description_withheld":null,"homepage":"https://betterup-data-requests.herokuapp.com/","introduced_date":"2022-03-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/advancing-an-interdisciplinary-science-of","title":"Advancing an Interdisciplinary Science of Conversation: Insights from a Large Multimodal Corpus of Human Speech","first_author":"Andrew Reece","url":null},"license":{"name":"see registration for details","url":"https://betterup-data-requests.herokuapp.com/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"},{"name":"Time series","url":"/datasets/modality/time-series"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Emotion Recognition in Conversation","url":"/task/emotion-recognition-in-conversation","datasets_with_task":"/datasets/task/emotion-recognition-in-conversation"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Facial Action Unit Detection","url":"/task/facial-action-unit-detection","datasets_with_task":"/datasets/task/facial-action-unit-detection"},{"name":"Recognizing Emotion Cause in Conversations","url":"/task/recognizing-emotion-cause-in-conversations","datasets_with_task":"/datasets/task/recognizing-emotion-cause-in-conversations"},{"name":"Video Emotion Recognition","url":"/task/video-emotion-recognition","datasets_with_task":"/datasets/task/video-emotion-recognition"},{"name":"Facial Emotion Recognition","url":"/task/facial-emotion-recognition","datasets_with_task":"/datasets/task/facial-emotion-recognition"},{"name":"Prosody Prediction","url":"/task/prosody-prediction","datasets_with_task":"/datasets/task/prosody-prediction"},{"name":"English Conversational Speech Recognition","url":"/task/english-conversational-speech-recognition","datasets_with_task":"/datasets/task/english-conversational-speech-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CANDOR Corpus"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}