{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:17:38Z","timestamp":1771697858906,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1109\/taslp.2017.2765834","type":"journal-article","created":{"date-parts":[[2017,10,23]],"date-time":"2017-10-23T19:17:53Z","timestamp":1508786273000},"page":"184-196","source":"Crossref","is-referenced-by-count":35,"title":["Progressive Joint Modeling in Unsupervised Single-Channel Overlapped Speech Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4400-5340","authenticated-orcid":false,"given":"Zhehuai","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jasha","family":"Droppo","sequence":"additional","affiliation":[]},{"given":"Jinyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Wayne","family":"Xiong","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178838"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1992.225858"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518545"},{"key":"ref31","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-251"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2163395"},{"key":"ref35","article-title":"Single-channel multi-talker speech recognition with permutation invariant training","author":"qian","year":"1707"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2945397"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref40","first-page":"1910","article-title":"Learning small-size DNN with output-distribution-based criteria","author":"li","year":"2014","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2700540"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-305"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389562"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-519"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953163"},{"key":"ref28","article-title":"Discriminative training for large vocabulary speech recognition","author":"povey","year":"2005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.006"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"2345","DOI":"10.21437\/Interspeech.2013-548","article-title":"Sequence-discriminative training of deep neural networks","author":"vesely","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.879814"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015050"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-655","article-title":"Single-channel speech separation using sparse non-negative matrix factorization","author":"schmidt","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1037\/11496-005"},{"key":"ref2","author":"bregman","year":"1994","journal-title":"Auditory Scene Analysis The Perceptual Organization of Sound"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"ref22","first-page":"806","article-title":"Large-vocabulary speech recognition under adverse acoustic environments","author":"deng","year":"2000","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639201"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639100"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953223"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2698723"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-852"},{"key":"ref44","article-title":"Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM","author":"hori","year":"1706"},{"key":"ref26","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1002\/rob.20276"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8124117\/08080252.pdf?arnumber=8080252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T23:25:06Z","timestamp":1719530706000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8080252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1]]},"references-count":44,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2765834","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1]]}}}