{"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/spgm-prioritizing-local-features-for-enhanced","title":"SPGM: Prioritizing Local Features for enhanced speech separation performance","arxiv_id":"2309.12608","date":"2023-09-22","proceeding":null,"authors":["Jia Qi Yip","Shengkui Zhao","Yukun Ma","Chongjia Ni","Chong Zhang","Hao Wang","Trung Hieu Nguyen","Kun Zhou","Dianwen Ng","Eng Siong Chng","Bin Ma"],"abstract":"Dual-path is a popular architecture for speech separation models (e.g. Sepformer) which splits long sequences into overlapping chunks for its intra- and inter-blocks that separately model intra-chunk local features and inter-chunk global relationships. However, it has been found that inter-blocks, which comprise half a dual-path model's parameters, contribute minimally to performance. Thus, we propose the Single-Path Global Modulation (SPGM) block to replace inter-blocks. SPGM is named after its structure consisting of a parameter-free global pooling module followed by a modulation module comprising only 2% of the model's total parameters. The SPGM block allows all transformer layers in the model to be dedicated to local feature modelling, making the overall model single-path. SPGM achieves 22.1 dB SI-SDRi on WSJ0-2Mix and 20.4 dB SI-SDRi on Libri2Mix, exceeding the performance of Sepformer by 0.5 dB and 0.3 dB respectively and matches the performance of recent SOTA models with up to 8 times fewer parameters. Model and weights are available at huggingface.co/yipjiaqi/spgm","url_abs":"https://arxiv.org/abs/2309.12608v2","url_pdf":"https://arxiv.org/pdf/2309.12608v2.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":"spgm-prioritizing-local-features-for-enhanced","repo_url":"https://huggingface.co/yipjiaqi/spgm","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"speech-separation","task_name":"Speech Separation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"SPGM + DM","rank_in_archive_order":12,"of":40,"metrics":{"MACs (G)":"77","Number of parameters (M)":"26.2","SI-SDRi":"22.7"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"SPGM","rank_in_archive_order":17,"of":40,"metrics":{"MACs (G)":"77","Number of parameters (M)":"26.2","SI-SDRi":"22.1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}