{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T02:59:53Z","timestamp":1784689193604,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2017,10,1]],"date-time":"2017-10-01T00:00:00Z","timestamp":1506816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100007696","name":"Oticon Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1109\/taslp.2017.2726762","type":"journal-article","created":{"date-parts":[[2017,7,13]],"date-time":"2017-07-13T18:33:12Z","timestamp":1499970792000},"page":"1901-1913","source":"Crossref","is-referenced-by-count":620,"title":["Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural Networks"],"prefix":"10.1109","volume":"25","author":[{"given":"Morten","family":"Kolbaek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2016.11.012"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref29","first-page":"91","article-title":"Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR","author":"weninger","year":"2015","journal-title":"LVA\/ICA"},{"key":"ref2","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":"Acustica United Acta Acustica"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref20","article-title":"Roles of pre-training and fine-tuning in context-dependent DBN-HMMs for real-world speech recognition","author":"yu","year":"2010","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"437","DOI":"10.21437\/Interspeech.2011-169","article-title":"Conversational speech transcription using context-dependent deep neural networks","author":"seide","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"ref24","article-title":"Achieving human parity in conversational speech recognition","author":"xiong","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-405"},{"key":"ref50","article-title":"CSR-I (WSJ0) complete LDC93s6a","author":"garofolo","year":"1993"},{"key":"ref51","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952120"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854890"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TASL.2012.2215591","article-title":"An unsupervised approach to cochannel speech separation","volume":"21","author":"hu","year":"2013","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref11","first-page":"2614","article-title":"Single-channel speech separation using sparse non-negative matrix factorization","author":"schmidt","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref40","article-title":"Single channel auditory source separation with neural network","author":"chen","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876726"},{"key":"ref13","article-title":"Sparse NMF half-baked or well done?","author":"roux","year":"2015"},{"key":"ref14","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"2000","journal-title":"Proc NIPS"},{"key":"ref15","first-page":"97","article-title":"Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system","author":"kristjansson","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref16","first-page":"89","article-title":"Speech recognition using factorial hidden markov models for separation in the feature space","author":"virtanen","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2047419"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007425814087"},{"key":"ref19","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.02.006"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref6","article-title":"Prediction-driven computational auditory scene analysis","author":"ellis","year":"1996"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/b99695"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref7","author":"cooke","year":"2005","journal-title":"Modelling Auditory Processing and Organisation"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.854106"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015061"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref48","article-title":"An introduction to computational networks and the computational network toolkit","author":"agarwal","year":"2014"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462371"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-64680-0_7","article-title":"Deep recurrent networks for separation and recognition of single channel speech in non-stationary background audio","author":"erdogan","year":"2017","journal-title":"New Era for Robust Speech Recognition Exploiting Deep Learning"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8015274\/07979557.pdf?arnumber=7979557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T13:42:41Z","timestamp":1692884561000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7979557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10]]},"references-count":55,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2017.2726762","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10]]}}}