{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T16:35:49Z","timestamp":1789835749500,"version":"4.0.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/jstsp.2019.2912565","type":"journal-article","created":{"date-parts":[[2019,4,25]],"date-time":"2019-04-25T22:34:39Z","timestamp":1556231679000},"page":"815-826","source":"Crossref","is-referenced-by-count":30,"title":["Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3683-5432","authenticated-orcid":false,"given":"Lukas","family":"Drude","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9468-7330","authenticated-orcid":false,"given":"Reinhold","family":"Haeb-Umbach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366611"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.898454"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2025790"},{"key":"ref70","first-page":"61-1","article-title":"Beamforming techniques for spatial filtering","author":"veen","year":"1997","journal-title":"Handbook for digital signal processing"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.3115\/1075527.1075614"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952163"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref38","first-page":"1","article-title":"Blind speech separation exploiting temporal and spectral correlations using 2D-HMMs","author":"vu","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref78","article-title":"CSR-I (WSJ0) Complete LDC93S6A","author":"garofolo","year":"1993","journal-title":"Web Download Philadelphia Linguistic Data Consortium"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref33","first-page":"1","article-title":"Normalized observation vector clustering approach for sparse source separation","author":"araki","year":"0","journal-title":"Eur Signal Process Conf"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2007.378164"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521385"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471653"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2277937"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050087"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2014.6954300"},{"key":"ref60","first-page":"1757","article-title":"On initial seed selection for frequency domain blind speech separation","author":"vu","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2297440"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638256"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref28","first-page":"241","article-title":"Blind speech separation employing directional statistics in an expectation maximization framework","author":"vu","year":"0","journal-title":"IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1768"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2029711"},{"key":"ref65","first-page":"1345","article-title":"Clustering on the unit hypersphere using von Mises-Fisher distributions","volume":"6","author":"banerjee","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2051355"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1969.7278"},{"key":"ref2","author":"wang","year":"2006","journal-title":"Computational Auditory Scene Analysis Principles Algorithms and Applications"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-305"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(94)90029-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1121\/1.1610463"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(98)00047-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.02.003"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.828896"},{"key":"ref50","article-title":"Speaker-independent speech separation with deep attractor network","author":"chen","year":"2017"},{"key":"ref51","first-page":"1","article-title":"An EM approach to integrated multichannel speech separation and noise suppression","author":"vu","year":"0","journal-title":"Proc Int Workshop Acoust Signal Enhancement"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(96)00043-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760429"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287865"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471718"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1994.tb01978.x"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854924"},{"key":"ref53","first-page":"988","article-title":"On the use of the Watson mixture model for clustering-based under-determined blind source separation","author":"jafari","year":"0","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00210"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/TASLP.2014.2364452","article-title":"A regression approach to speech enhancement based on deep neural networks","volume":"23","author":"xu","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015061"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2580946"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.10.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462646"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952155"},{"key":"ref82","first-page":"12","article-title":"Wide residual BLSTM network with discriminative speaker adaptation for robust speech recognition","author":"heymann","year":"0","journal-title":"Proc Int Workshop Speech Process Everyday Environ"},{"key":"ref81","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref17","article-title":"Monaural audio speaker separation with source contrastive estimation","author":"stephenson","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462462"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref83","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"Proc IEEE Workshop Autom Speech Recognit Understanding"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885253"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.21236\/ADA307097"},{"key":"ref5","article-title":"Sparse NMF–half-baked or well done","author":"roux","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.938081"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref7","first-page":"97","article-title":"Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system","author":"kristjansson","year":"0","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref45","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013"},{"key":"ref48","article-title":"Structured vaes: Composing probabilistic graphical models and variational autoencoders","author":"johnson","year":"2016"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461336"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-187"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1250\/ast.22.149"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/78.149989"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/8771267\/08695037.pdf?arnumber=8695037","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:08:16Z","timestamp":1657746496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8695037\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":84,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2019.2912565","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}