{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:43:34Z","timestamp":1783104214139,"version":"3.54.6"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3099291","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T22:22:21Z","timestamp":1627338141000},"page":"2840-2849","source":"Crossref","is-referenced-by-count":170,"title":["Wavesplit: End-to-End Speech Separation by Speaker Clustering"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-3987","authenticated-orcid":false,"given":"Neil","family":"Zeghidour","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8847-9532","authenticated-orcid":false,"given":"David","family":"Grangier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054719"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462505"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053038"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref74","year":"0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682572"},{"key":"ref75","year":"0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/37\/5\/627"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462661"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-811"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683087"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461778"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683448"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004016"},{"key":"ref60","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref62","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","article-title":"Spreading vectors for similarity search","author":"sablayrolles","year":"0","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952158"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462471"},{"key":"ref64","article-title":"Demucs: Deep extractor for music sources with extra unlabeled data remixed","author":"d\u00e9fossez","year":"0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref65","year":"0"},{"key":"ref66","article-title":"CSR-I (WSJ0) complete,” Linguistic Data Consortium","author":"garofolo","year":"1993"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_53"},{"key":"ref67","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"cosentino","year":"0"},{"key":"ref68","year":"0"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref2","article-title":"Sokoto coventry fingerprint dataset","author":"shehu","year":"0"},{"key":"ref1","first-page":"1","article-title":"An electrical load measurements dataset of United Kingdom households from a two-year longitudinal study","volume":"4","author":"murray","year":"2017","journal-title":"Data Science Journal"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref21","first-page":"1991","article-title":"Underdetermined blind speech separation with directivity pattern based continuous mask and ICA","author":"araki","year":"0","journal-title":"Proc 12th Eur Signal Process Conf"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref50","article-title":"Layer normalization","author":"ba","year":"0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref59","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"n","year":"0","journal-title":"J Mach Learn Res"},{"key":"ref58","article-title":"What’s all the fuss about free universal sound separation data","author":"wisdom","year":"0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref56","article-title":"The ami meeting corpus","author":"mccowan","year":"0","journal-title":"Proc 5th Int Conf Methods Techn Behav Res"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref53","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc Social Serv Wheels Int Symp Comput Architecture"},{"key":"ref52","article-title":"Film: Visual reasoning with a general conditioning layer","author":"perez","year":"0","journal-title":"Proc 32nd Assoc Adv Artif Intell Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054572"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref13","article-title":"Voice separation with an unknown number of multiple speakers","author":"nachmani","year":"0"},{"key":"ref14","article-title":"VoiceFilter: Targeted voice separation by speaker-conditioned spectrogram masking","author":"wang","year":"2018"},{"key":"ref15","first-page":"793","article-title":"One microphone source separation","author":"roweis","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref18","author":"williamson","year":"2012","journal-title":"Discrete-Time Signal Processing An Algebraic Approach Ser Advanced Textbooks in Control and Signal Processing"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.pnmrs.2014.06.002"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3847\/1538-3881\/aa9e09"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683007"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref7","article-title":"The MUSDB18 corpus for music separation","author":"rafii","year":"2017"},{"key":"ref49","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"0","journal-title":"Proc 4th Int Conf Learn Represent ICLR 2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref46","first-page":"626","author":"roux","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-017-0868-3"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1980.1094577"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1097\/GCO.0b013e328337233c"},{"key":"ref41","article-title":"Exploring the time-domain deep attractor network with two-stream architectures in a reverberant environment","author":"chen","year":"0"},{"key":"ref44","article-title":"Noninvasive fetal ECG: The physionet\/computing in cardiology challenge 2013","author":"silva","year":"0","journal-title":"Comput Cardiol"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3414\/ME09-01-0041"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09495162.pdf?arnumber=9495162","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:56Z","timestamp":1652194436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9495162\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3099291","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}