{"url":"/dataset/olkavs","name":"OLKAVS","full_name":"An Open Large-Scale Korean Audio-Visual Speech Dataset","description_markdown":"The dataset contains 1,150 hours of transcribed audio from 1,107 Korean speakers in a studio setup with nine different viewpoints and various noise situations. We also provide the pre-trained baseline models for two tasks, audio-visual speech recognition and lip reading.","description_withheld":null,"homepage":"https://aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=realm&dataSetSn=538","introduced_date":"2023-01-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/olkavs-an-open-large-scale-korean-audio","title":"OLKAVS: An Open Large-Scale Korean Audio-Visual Speech Dataset","first_author":"Jeongkyun Park","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["OLKAVS"],"data_loaders":[],"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."}