{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T22:23:07Z","timestamp":1769552587169,"version":"3.49.0"},"reference-count":97,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091302006"],"award-info":[{"award-number":["ZDSYS20230626091302006"]}]},{"name":"Shenzhen Science and Technology Research Fund","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3446242","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T15:47:50Z","timestamp":1724168870000},"page":"4184-4198","source":"Crossref","is-referenced-by-count":7,"title":["Speech Separation With Pretrained Frontend to Minimize Domain Mismatch"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5360-2054","authenticated-orcid":false,"given":"Wupeng","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8106-1176","authenticated-orcid":false,"given":"Zexu","family":"Pan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Singapore"}]},{"given":"Xinke","family":"Li","sequence":"additional","affiliation":[{"name":"Industrial Systems Engineering and Management, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1523-9631","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"117","article-title":"The cocktail party phenomenon: A review of research on speech intelligibility in multiple-talker conditions","volume":"86","author":"Bronkhorst","year":"2000","journal-title":"Acta Acustica United Acustica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1410"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3100682"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3143036"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004035"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1193"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747239"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3010163"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2851-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326686"},{"issue":"1","key":"ref12","first-page":"1","article-title":"Blind source separation and independent component analysis: A review","volume":"6","author":"Choi","year":"2005","journal-title":"Neural Inf. Process.- Lett. Rev."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854302"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-218"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1983.1171927"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881700"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref25","article-title":"Librimix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746662"},{"key":"ref29","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wisdom","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200911"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3232276"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1243"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-023-00273-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747855"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3182271"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.692"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref41","volume-title":"The Auditory Brainstem: A Review of the Structure and Function of Auditory Brainstem Processing Mechanisms","author":"Irvine","year":"2012"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1097\/01.aud.0000240507.83072.e7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00524"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3758\/BF03212667"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1126\/science.176.4039.1149"},{"key":"ref46","article-title":"A theory and computational model of auditory monaural sound separation","author":"Weintraub","year":"1985"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.5772\/16613"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3191845"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054438"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054458"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3095662"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383575"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1228"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053176"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096876"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref57","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"33","author":"Baevski","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747077"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389642"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094883"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096630"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096603"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3383794"},{"key":"ref67","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095591"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095373"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3332545"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.580"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1177\/107769905303000401"},{"key":"ref75","first-page":"419","article-title":"A fast and simple algorithm for training neural probabilistic language models","volume-title":"Proc. 29th Int. Conf. Int. Conf. Mach. Learn.","author":"Mnih","year":"2012"},{"key":"ref76","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist. JMLR Workshop Conf. Proc.","author":"Gutmann","year":"2010"},{"key":"ref77","article-title":"Exploring the limits of language modeling","author":"Jozefowicz","year":"2016"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1038\/4580"},{"key":"ref79","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin","year":"2015"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023218"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036611"},{"issue":"1","key":"ref83","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref86","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"33","author":"Caron","year":"2020"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref88","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref89","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref90","article-title":"An efficient encoder-decoder architecture with top-down attention for speech separation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Li","year":"2023"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-236"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3038"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10640238.pdf?arnumber=10640238","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T17:32:29Z","timestamp":1727285549000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10640238\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":97,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3446242","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}