{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:13Z","timestamp":1774420093020,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888528","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Multiple Choice Learning for Efficient Speech Separation with Many Speakers"],"prefix":"10.1109","author":[{"given":"David","family":"Perera","sequence":"first","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fran\u00e7ois","family":"Derrida","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Th\u00e9o","family":"Mariotte","sequence":"additional","affiliation":[{"name":"Le Mans Université,LIUM,Le Mans,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ga\u00ebl","family":"Richard","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Slim","family":"Essid","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,LTCI, Télécom Paris,France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.3675001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3350887"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287816"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.3036175"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2157689.2157834"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446032"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref11","article-title":"SepIt: Approaching a single channel speech separation bound","volume-title":"type: article","author":"Lutati"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-493"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/321694.321699"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414508"},{"key":"ref22","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Annealed multiple choice learning: Overcoming limitations of winner-takes-all with annealing","author":"Perera","year":"2024"},{"key":"ref24","article-title":"Multiple choice learning: Learning to produce multiple structured outputs","volume":"25","author":"Guzman-Rivera","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref25","article-title":"Stochastic multiple choice learning for training diverse deep ensembles","volume":"29","author":"Lee","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC45102.2020.9294420"},{"key":"ref27","first-page":"7164","article-title":"Voice separation with an unknown number of multiple speakers","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Nachmani"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.388"},{"key":"ref30","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref32","first-page":"46","article-title":"Dual-path RNN: Efficient long sequence modeling for time-domain single-channel speech separation","volume-title":"International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Luo"},{"key":"ref33","first-page":"21","article-title":"Attention is all you need in speech separation","volume-title":"International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Subakan"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096646"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937253"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2000.0705"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10612-2"},{"key":"ref39","article-title":"Resilient multiple choice learning: A learned scoring scheme with application to audio scene analysis","volume":"36","author":"Letzelter","year":"2024","journal-title":"Advances in neural information processing systems"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10888528.pdf?arnumber=10888528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:21Z","timestamp":1774416381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888528","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}