{"url":"/dataset/ci-avsr","name":"CI-AVSR","full_name":null,"description_markdown":"**Cantonese In-car Audio-Visual Speech Recognition** (**CI-AVSR**) is a dataset for in-car command recognition in the Cantonese language with both video and audio data. It consists of 4,984 samples (8.3 hours) of 200 in-car commands recorded by 30 native Cantonese speakers. Furthermore, the dataset is augmented using common in-car background noises to simulate real environments, producing a dataset 10 times larger than the collected one.","description_withheld":null,"homepage":"https://github.com/HLTCHKUST/CI-AVSR","introduced_date":"2022-01-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/ci-avsr-a-cantonese-audio-visual-speech","title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","first_author":"Wenliang Dai","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[],"variants":["CI-AVSR"],"data_loaders":[{"repo":"https://github.com/hltchkust/ci-avsr","url":"https://drive.google.com/file/d/1ov4hfcL4oPncE6H4ZeAwJRp9dpUJP1Zr/view?usp=sharing","frameworks":["pytorch"]}],"num_papers_in_archive":2,"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."}