{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T14:05:31Z","timestamp":1782482731189,"version":"3.54.5"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7471631","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"31-35","source":"Crossref","is-referenced-by-count":886,"title":["Deep clustering: Discriminative embeddings for segmentation and separation"],"prefix":"10.1109","author":[{"given":"John R.","family":"Hershey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Recursive context propagation network for semantic scene labeling","author":"sharma","year":"2014","journal-title":"Proc NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/1687-4722-2013-14"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref10","article-title":"Underdetermined source separation using speaker subspace models","author":"weiss","year":"2009"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-22482-4_11","article-title":"Speech enhancement with lstm recurrent neural networks and its application to noise-robust asr","author":"weninger","year":"2015","journal-title":"Latent Variable Analysis and Signal Separation"},{"key":"ref12","article-title":"On training targets for supervised speech separation","volume":"22","author":"wang","year":"2014","journal-title":"Audio Speech and Language Processing IEEE\/ACM Transactions on"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref14","article-title":"Modelling auditory processing and organisation","author":"cooke","year":"1991"},{"key":"ref15","article-title":"Prediction-driven computational auditory scene analysis","author":"ellis","year":"1996"},{"key":"ref16","article-title":"Learning spectral clustering, with application to speech separation","volume":"7","author":"bach","year":"2006","journal-title":"JMLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1037\/11496-005"},{"key":"ref18","article-title":"An unsupervised approach to cochannel speech separation","volume":"21","author":"hu","year":"2013","journal-title":"Audio Speech and Language Processing IEEE Transactions on"},{"key":"ref19","article-title":"Normalized cuts and image segmentation","volume":"22","author":"shi","year":"2000","journal-title":"IEEE Trans PAMI"},{"key":"ref28","article-title":"Sparse NMF - half-baked or well done?","author":"le roux","year":"2015","journal-title":"Tech Rep TR2015–023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2221459"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876726"},{"key":"ref3","article-title":"Towards scaling up classification-based speech separation","volume":"21","author":"wang","year":"2013","journal-title":"IEEE Trans Audio Speech Language Process"},{"key":"ref6","article-title":"Joint optimization of masks and deep recurrent neural networks for monaural source separation","author":"huang","year":"2015","journal-title":"arXiv preprint arXiv 1502 01032"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.938081"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-23","article-title":"Speech recognition using factorial hidden markov models for separation in the feature space","author":"virtanen","year":"2006","journal-title":"Proc Interspeech 2006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.006"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1486.001.0001","article-title":"Auditory scene analysis: The perceptual organization of sound","author":"bregman","year":"1990"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8916","article-title":"Learning deep representations for graph clustering","author":"tian","year":"2014","journal-title":"Proc AAAI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1262185"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.272"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.1007\/s10994-011-5267-2","article-title":"Local equivalences of distances between clusteringsa geometric perspective","volume":"86","author":"meil\u00e4","year":"2012","journal-title":"Machine Learning"},{"key":"ref26","article-title":"Deep clustering: Discriminative embeddings for segmentation and separation","author":"hershey","year":"2015"},{"key":"ref25","article-title":"The stability of a good clustering","author":"meila","year":"2014","journal-title":"University of Washington Department of Statistics vol Technical Report 624"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Shanghai","start":{"date-parts":[[2016,3,20]]},"end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07471631.pdf?arnumber=7471631","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,2]],"date-time":"2022-07-02T03:42:01Z","timestamp":1656733321000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7471631\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7471631","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}