{"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/wavesplit-end-to-end-speech-separation-by","title":"Wavesplit: End-to-End Speech Separation by Speaker Clustering","arxiv_id":"2002.08933","date":"2020-02-20","proceeding":null,"authors":["Neil Zeghidour","David Grangier"],"abstract":"We introduce Wavesplit, an end-to-end source separation system. From a single mixture, the model infers a representation for each source and then estimates each source signal given the inferred representations. The model is trained to jointly perform both tasks from the raw waveform. Wavesplit infers a set of source representations via clustering, which addresses the fundamental permutation problem of separation. For speech separation, our sequence-wide speaker representations provide a more robust separation of long, challenging recordings compared to prior work. Wavesplit redefines the state-of-the-art on clean mixtures of 2 or 3 speakers (WSJ0-2/3mix), as well as in noisy and reverberated settings (WHAM/WHAMR). We also set a new benchmark on the recent LibriMix dataset. Finally, we show that Wavesplit is also applicable to other domains, by separating fetal and maternal heart rates from a single abdominal electrocardiogram.","url_abs":"https://arxiv.org/abs/2002.08933v2","url_pdf":"https://arxiv.org/pdf/2002.08933v2.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":"abstracts"},"code_links":[],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-whamr","task":"Speech Separation","dataset":"WHAMR!","model":"Wavesplit","rank_in_archive_order":9,"of":18,"metrics":{"SI-SDRi":"13.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"Wavesplit v2","rank_in_archive_order":16,"of":40,"metrics":{"SDRi":"22.3","SI-SDRi":"22.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"Wavesplit v1","rank_in_archive_order":27,"of":40,"metrics":{"SI-SDRi":"19.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2002.08933","atlas_url":"https://app.syntology.ai/?focus=2002.08933","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}