{"url":"/dataset/musan","name":"MUSAN","full_name":null,"description_markdown":"**MUSAN** is a corpus of music, speech and noise. This dataset is suitable for training models for voice activity detection (VAD) and music/speech discrimination. The dataset consists of music from several genres, speech from twelve languages, and a wide assortment of technical and non-technical noises.","description_withheld":null,"homepage":"http://www.openslr.org/17/","introduced_date":"2015-10-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/musan-a-music-speech-and-noise-corpus","title":"MUSAN: A Music, Speech, and Noise Corpus","first_author":null,"url":null},"license":{"name":"CC BY 4.0","url":null},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"},{"name":"Music","url":"/datasets/modality/music"}],"tasks":[],"languages":[],"variants":["MUSAN"],"data_loaders":[],"num_papers_in_archive":204,"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."}