{"url":"/dataset/usc","name":"USC","full_name":"Uzbek Speech Corpus","description_markdown":"The Uzbek speech corpus (USC) comprises 958 different speakers with a total of 105 hours of transcribed audio recordings. This is the first open-source Uzbek speech corpus dedicated to the ASR task.\r\n\r\nSource: [USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments](https://paperswithcode.com/paper/usc-an-open-source-uzbek-speech-corpus-and)","description_withheld":null,"homepage":"","introduced_date":"2021-07-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/usc-an-open-source-uzbek-speech-corpus-and","title":"USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments","first_author":"Muhammadjon Musaev","url":null},"license":{"name":"Creative Commons Attribution 4.0 International","url":"https://github.com/IS2AI/Uzbek_ASR/blob/main/LICENSE.md"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[],"languages":[{"name":"Uzbek","url":"/datasets/language/uzbek"}],"variants":["USC"],"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."}