{"url":"/dataset/cas-vsr-s101","name":"CAS-VSR-S101","full_name":null,"description_markdown":"A new large-scale, in-thewild Mandarin dataset, CAS-VSR-S101 with 101.1 hours of data. The videos are sourced from broadcast news and conversational programs in Chinese, covering a highly diverse set of topics, speakers and filming conditions. The lengths of the utterances are naturally distributed between 0.01s and 10.57s, and image qualities and resolutions vary. News accounts for 82.4% of the programs. 70.4% of the utterances depict news anchors, hosts and correspondents, while 29.6% are those of interviewees and guests. In addition, at a ratio of approximately 1.5 : 1, male and female appearances are relatively balanced. It is divided into train, validation and test sets by TV channels to minimize speaker\r\noverlap, and at a ratio of roughly 8 : 1 : 1.5 in terms of duration. The validation and test sets are composed of programs broadcast on provincial TV channels. \r\nThe dataset is available for academic use under a license.","description_withheld":null,"homepage":"https://github.com/VIPL-Audio-Visual-Speech-Understanding/CAS-VSR-S101","introduced_date":"2024-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/es3-evolving-self-supervised-learning-of","title":"ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations","first_author":"Yuanhang Zhang","url":null},"license":{"name":"Free for academic use","url":"https://github.com/VIPL-Audio-Visual-Speech-Understanding/CAS-VSR-S101"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Speech Enhancement","url":"/task/speech-enhancement","datasets_with_task":"/datasets/task/speech-enhancement"},{"name":"Lipreading","url":"/task/lipreading","datasets_with_task":"/datasets/task/lipreading"},{"name":"Audio-Visual Speech Recognition","url":"/task/audio-visual-speech-recognition","datasets_with_task":"/datasets/task/audio-visual-speech-recognition"},{"name":"Lip Reading","url":"/task/lip-reading","datasets_with_task":"/datasets/task/lip-reading"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CAS-VSR-S101"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/audio-visual-speech-recognition-on-cas-vsr","task":"Audio-Visual Speech Recognition","dataset_variant":"CAS-VSR-S101","rows":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"ES³ Base*","paper":"/paper/es3-evolving-self-supervised-learning-of","metrics":{"Word Error Rate (WER)":"11.0"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/lipreading-on-cas-vsr-s101","task":"Lipreading","dataset_variant":"CAS-VSR-S101","rows":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"ES³ Base*","paper":"/paper/es3-evolving-self-supervised-learning-of","metrics":{"Word Error Rate (WER)":"55.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speech-recognition-on-cas-vsr-s101","task":"Speech Recognition","dataset_variant":"CAS-VSR-S101","rows":1,"metrics":["Word Error Rate (WER)"],"first_row_in_archive_order":{"model":"ES³ Base*","paper":"/paper/es3-evolving-self-supervised-learning-of","metrics":{"Word Error Rate (WER)":"11.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/es3-evolving-self-supervised-learning-of","title":"ES3: Evolving Self-Supervised Learning of Robust Audio-Visual Speech Representations","date":"2024-01-01","rows_on_this_dataset":3,"code_links":0,"syntology":null}],"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."}