{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:30:00Z","timestamp":1778347800695,"version":"3.51.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2015,12,1]],"date-time":"2015-12-01T00:00:00Z","timestamp":1448928000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-09-1-0383"],"award-info":[{"award-number":["W911NF-09-1-0383"]}],"id":[{"id":"10.13039\/100000183","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":[[2015,12]]},"DOI":"10.1109\/taslp.2015.2468583","type":"journal-article","created":{"date-parts":[[2015,8,14]],"date-time":"2015-08-14T15:01:02Z","timestamp":1439564462000},"page":"2136-2147","source":"Crossref","is-referenced-by-count":348,"title":["Joint Optimization of Masks and Deep Recurrent Neural Networks for Monaural Source Separation"],"prefix":"10.1109","volume":"23","author":[{"family":"Po-Sen Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Minje Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Hasegawa-Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paris","family":"Smaragdis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032183"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.899291"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"},{"key":"ref31","first-page":"443","author":"williams","year":"1995","journal-title":"?Gradient-based learning algorithms for recurrent networks and their computational complexity ? Backpropagation Theory Architectures and Applications"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424210"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1137\/0916069"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178296"},{"key":"ref10","article-title":"A probabilistic latent variable model for acoustic modeling","volume":"148","author":"smaragdis","year":"2006","journal-title":"Proc Adv Models Acoust Process Neural Inf Process Syst Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","article-title":"Singing-voice separation from monaural recordings using deep recurrent neural networks","author":"huang","year":"2014","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref13","author":"kabal","year":"0","journal-title":"?TSP speech database ?"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2026503"},{"key":"ref15","author":"garofolo","year":"1993","journal-title":"?TIMIT Acoustic-phonetic Continuous Speech Corpus ?"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref17","first-page":"2685","article-title":"Experiments on deep learning for speech denoising","author":"liu","year":"2014","journal-title":"Proc 15th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/1084713808326455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854294"},{"key":"ref4","article-title":"Low-rank representation of both singing voice and music accompaniment via learned dictionaries","author":"yang","year":"2013","journal-title":"Proc 11th Int Soc Music Inf Retrieval Conf (ISMIR)"},{"key":"ref28","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume":"15","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref3","article-title":"Real-time online singing voice separation from monaural recordings using robust low-rank modeling","author":"sprechmann","year":"2012","journal-title":"Proc Int Society for Music Inf Retrieval Conf (ISMIR)"},{"key":"ref27","article-title":"How to construct deep recurrent neural networks","author":"pascanu","year":"2014","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2396305"},{"key":"ref29","first-page":"349","article-title":"A focused back-propagation algorithm for temporal pattern recognition","volume":"3","author":"mozer","year":"1989","journal-title":"Complex Syst"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/44565","article-title":"Learning the parts of objects by non-negative matrix factorization","volume":"401","author":"lee","year":"1999","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref2","first-page":"22","article-title":"Recurrent neural networks for noise reduction in robust ASR","author":"maas","year":"2012","journal-title":"Proc 13th Annu Conf Int Speech Commun Assoc (INTERSPEECH)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/312624.312649"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287816"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854890"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2250961"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015061"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref26","first-page":"190","article-title":"Training and analysing deep recurrent neural networks","author":"hermans","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854299"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7243388\/07194774.pdf?arnumber=7194774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:03:27Z","timestamp":1642003407000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7194774\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2015.2468583","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,12]]}}}