{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:06:04Z","timestamp":1771697164269,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1109\/mlsp.2017.8168152","type":"proceedings-article","created":{"date-parts":[[2017,12,13]],"date-time":"2017-12-13T14:22:14Z","timestamp":1513174934000},"page":"1-6","source":"Crossref","is-referenced-by-count":8,"title":["Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant training"],"prefix":"10.1109","author":[{"given":"Morten","family":"Kolbaek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng-Hua","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jesper","family":"Jensen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref31","article-title":"An introduction to computational networks and the computational network toolkit","author":"agarwal","year":"2014","journal-title":"Microsoft Technical Report MSR-TR –2014–112 Tech Rep"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899233"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1201\/b14529","author":"loizou","year":"2013","journal-title":"Speech Enhancement Theory and Practice"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref11","first-page":"31","article-title":"Deep clustering: Discriminative em-beddings for segmentation and separation","author":"hershey","year":"2016","journal-title":"Proc ICASSP"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2444659"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref16","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"ref19","author":"xiong","year":"2016","journal-title":"Achieving human parity in conversational speech recognition"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.IR.4930"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-551"},{"key":"ref27","first-page":"56","year":"1993","journal-title":"ITU Rec P 56 Objective measurement of active speech level"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2628641"},{"key":"ref6","first-page":"577","article-title":"Discriminatively trained recurrent neural networks for single-channel speech separation","author":"weninger","year":"2014","journal-title":"The global"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404837"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.4948445"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2009.09.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015050"},{"key":"ref1","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":"Acta Acust United Ac"},{"key":"ref20","author":"saon","year":"2017","journal-title":"English conversational telephone speech recognition by humans and machines"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.heares.2016.11.012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1121\/1.4929493"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_7"},{"key":"ref26","article-title":"CSR-I (WSJ0) Complete LDC93s6a","author":"garofolo","year":"1993","journal-title":"Philadelphia Linguistic Data Consortium"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"}],"event":{"name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Tokyo","start":{"date-parts":[[2017,9,25]]},"end":{"date-parts":[[2017,9,28]]}},"container-title":["2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8122073\/8168099\/08168152.pdf?arnumber=8168152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,7]],"date-time":"2019-10-07T20:15:59Z","timestamp":1570479359000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8168152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/mlsp.2017.8168152","relation":{},"subject":[],"published":{"date-parts":[[2017,9]]}}}