{"url":"/dataset/laborotvspeech","name":"LaboroTVSpeech","full_name":null,"description_markdown":"LaboroTVSpeech is a large-scale Japanese speech corpus built from broadcast TV recordings and their subtitles. It contains over 2,000 hours of speech.","description_withheld":null,"homepage":"https://github.com/laboroai/LaboroTVSpeech","introduced_date":"2021-03-26","introduced_date_note":null,"introduced_by":{"paper":"/paper/construction-of-a-large-scale-japanese-asr","title":"Construction of a Large-scale Japanese ASR Corpus on TV Recordings","first_author":"Shintaro Ando","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[],"languages":[{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["LaboroTVSpeech"],"data_loaders":[{"repo":"https://github.com/laboroai/LaboroTVSpeech","url":"https://github.com/laboroai/LaboroTVSpeech","frameworks":[]}],"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."}