{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/musan-a-music-speech-and-noise-corpus","title":"MUSAN: A Music, Speech, and Noise Corpus","arxiv_id":"1510.08484","date":"2015-10-28","proceeding":null,"authors":["David Snyder","Guoguo Chen","Daniel Povey"],"abstract":"This report introduces a new corpus of music, speech, and noise. This dataset is suitable for training models for voice activity detection (VAD) and music/speech discrimination. Our corpus is released under a flexible Creative Commons license. The dataset consists of music from several genres, speech from twelve languages, and a wide assortment of technical and non-technical noises. We demonstrate use of this corpus for music/speech discrimination on Broadcast news and VAD for speaker identification.","url_abs":"http://arxiv.org/abs/1510.08484v1","url_pdf":"http://arxiv.org/pdf/1510.08484v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"musan-a-music-speech-and-noise-corpus","repo_url":"https://github.com/Jasson-Chen/Add_noise_and_rir_to_speech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"musan-a-music-speech-and-noise-corpus","repo_url":"https://github.com/JerryPeng21cuhk/prj_broadcast","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"musan","name":"MUSAN","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1510.08484","atlas_url":"https://app.syntology.ai/?focus=1510.08484","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}