{"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/self-supervised-pre-training-reduces-label","title":"Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training","arxiv_id":"2010.15366","date":"2020-10-29","proceeding":null,"authors":["Sung-Feng Huang","Shun-Po Chuang","Da-Rong Liu","Yi-Chen Chen","Gene-Ping Yang","Hung-Yi Lee"],"abstract":"Speech separation has been well developed, with the very successful permutation invariant training (PIT) approach, although the frequent label assignment switching happening during PIT training remains to be a problem when better convergence speed and achievable performance are desired. In this paper, we propose to perform self-supervised pre-training to stabilize the label assignment in training the speech separation model. Experiments over several types of self-supervised approaches, several typical speech separation models and two different datasets showed that very good improvements are achievable if a proper self-supervised approach is chosen.","url_abs":"https://arxiv.org/abs/2010.15366v3","url_pdf":"https://arxiv.org/pdf/2010.15366v3.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":[{"paper_slug":"self-supervised-pre-training-reduces-label","repo_url":"https://github.com/SungFeng-Huang/SSL-pretraining-separation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speaker-separation","task_name":"Speaker Separation"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-libri2mix","task":"Speech Separation","dataset":"Libri2Mix","model":"Conv-Tasnet (Libri1Mix speech enhancement pre-trained)","rank_in_archive_order":8,"of":10,"metrics":{"SDRi":"14.6","SI-SDRi":"14.1"},"uses_additional_data":true},{"leaderboard":"/sota/speech-separation-on-libri2mix","task":"Speech Separation","dataset":"Libri2Mix","model":"Conv-Tasnet (Libri1Mix speech enhancement multi-task)","rank_in_archive_order":9,"of":10,"metrics":{"SDRi":"14.1","SI-SDRi":"13.7"},"uses_additional_data":true},{"leaderboard":"/sota/speech-separation-on-libri2mix","task":"Speech Separation","dataset":"Libri2Mix","model":"Conv-Tasnet","rank_in_archive_order":10,"of":10,"metrics":{"SDRi":"13.6","SI-SDRi":"13.2"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"DPTNet (Libri1Mix speech enhancement pre-trained)","rank_in_archive_order":19,"of":40,"metrics":{"SDRi":"21.5","SI-SDRi":"21.3"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}