{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:20:30Z","timestamp":1777656030676,"version":"3.51.4"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2013,7,1]],"date-time":"2013-07-01T00:00:00Z","timestamp":1372636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2013,7]]},"DOI":"10.1109\/tasl.2013.2250961","type":"journal-article","created":{"date-parts":[[2013,3,22]],"date-time":"2013-03-22T18:02:35Z","timestamp":1363975355000},"page":"1381-1390","source":"Crossref","is-referenced-by-count":366,"title":["Towards Scaling Up Classification-Based Speech Separation"],"prefix":"10.1109","volume":"21","author":[{"family":"Yuxuan Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"DeLiang Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.03.006"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1121\/1.1610463"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"ref32","first-page":"1","article-title":"Exploring strategies for training deep neural networks","volume":"10","author":"larochelle","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.08.005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/1.3184603"},{"key":"ref37","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","author":"platt","year":"1999","journal-title":"Adv Large Margin Classifiers"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172425"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109382"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1121\/1.2832617"},{"key":"ref10","article-title":"The importance of encoding versus training with sparse coding and vector quantization","author":"coates","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273598"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","article-title":"Context-dependent pre-trained deep neural networks for large vocabulary speech recognition","volume":"20","author":"dahl","year":"2012","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref13","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref14","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.04-08-771"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.4930"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.4754541"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947430"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495680"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2077280"},{"key":"ref4","first-page":"1579","article-title":"Fast kernel classifiers with online and active learning","volume":"6","author":"bordes","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1109\/TASL.2008.2010633","article-title":"A supervised learning approach to monaural segregation of reverberant speech","volume":"17","author":"jin","year":"2009","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.2363929"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1109\/TASL.2010.2041116","article-title":"Improving speech intelligibility in noise using environment-optimized algorithms","volume":"18","author":"kim","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref5","first-page":"161","article-title":"The tradeoffs of large scale learning","author":"bottou","year":"2008","journal-title":"Adv Neural Inf Process Syst 20"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-552"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref2","author":"boersma","year":"2005","journal-title":"Praat Doing phonetics by computer (Version 4 3 14)"},{"key":"ref9","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000006"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221459"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref45","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref47","first-page":"224","article-title":"Cocktail party processing via structured prediction","author":"wang","year":"2012","journal-title":"Adv Neural Inf Process Syst 25"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref42","first-page":"131","article-title":"Distances between data sets based on summary statistic","volume":"8","author":"tatti","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.2939132"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1251146"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAU.1969.1162058"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref25","author":"hu","year":"2004","journal-title":"100 nonspeech environmental sounds"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376\/6484971\/06473841.pdf?arnumber=6473841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T17:09:29Z","timestamp":1640279369000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6473841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7]]},"references-count":47,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2013.2250961","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,7]]}}}