{"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/sepmamba-state-space-models-for-speaker","title":"SepMamba: State-space models for speaker separation using Mamba","arxiv_id":"2410.20997","date":"2024-10-28","proceeding":null,"authors":["Thor Højhus Avenstrup","Boldizsár Elek","István László Mádi","András Bence Schin","Morten Mørup","Bjørn Sand Jensen","Kenny Falkær Olsen"],"abstract":"Deep learning-based single-channel speaker separation has improved significantly in recent years largely due to the introduction of the transformer-based attention mechanism. However, these improvements come at the expense of intense computational demands, precluding their use in many practical applications. As a computationally efficient alternative with similar modeling capabilities, Mamba was recently introduced. We propose SepMamba, a U-Net-based architecture composed primarily of bidirectional Mamba layers. We find that our approach outperforms similarly-sized prominent models - including transformer-based models - on the WSJ0 2-speaker dataset while enjoying a significant reduction in computational cost, memory usage, and forward pass time. We additionally report strong results for causal variants of SepMamba. Our approach provides a computationally favorable alternative to transformer-based architectures for deep speech separation.","url_abs":"https://arxiv.org/abs/2410.20997v1","url_pdf":"https://arxiv.org/pdf/2410.20997v1.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":"sepmamba-state-space-models-for-speaker","repo_url":"https://github.com/andrasschin/SepMamba","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"speaker-separation","task_name":"Speaker Separation"},{"task_slug":"speech-separation","task_name":"Speech Separation"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"mamba","method_name":"Mamba"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"SepMamba + DM (M)","rank_in_archive_order":11,"of":40,"metrics":{"SDRi":"22.9","SI-SDRi":"22.7"},"uses_additional_data":false},{"leaderboard":"/sota/speech-separation-on-wsj0-2mix","task":"Speech Separation","dataset":"WSJ0-2mix","model":"SepMamba + DM (S)","rank_in_archive_order":20,"of":40,"metrics":{"SDRi":"21.4","SI-SDRi":"21.2"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}