{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,7]],"date-time":"2026-06-07T16:56:18Z","timestamp":1780851378992,"version":"3.54.1"},"reference-count":149,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3235010","type":"journal-article","created":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T20:50:13Z","timestamp":1673297413000},"page":"4242-4269","source":"Crossref","is-referenced-by-count":22,"title":["State-of-the-Art Analysis of Deep Learning-Based Monaural Speech Source Separation Techniques"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1147-3877","authenticated-orcid":false,"given":"Swati","family":"Soni","sequence":"first","affiliation":[{"name":"Department of Electronics and Communication Engineering, Maulana Azad National Institute of Technology, Bhopal, Madhya Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ram Narayan","family":"Yadav","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Maulana Azad National Institute of Technology, Bhopal, Madhya Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lalita","family":"Gupta","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Maulana Azad National Institute of Technology, Bhopal, Madhya Pradesh, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3171967"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnsre.2021.3125314"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3142918"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2012.2214786"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2296173"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2261814"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057198"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3165712"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4084951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3188712"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3019495"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3147514"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3169629"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2022.3155271"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1002\/9781119861850.ch13"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/prml56267.2022.9882231"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s40708-015-0016-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICOT.2015.7498486"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2009.5396022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.465"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/1084713808326455"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-498"},{"key":"ref28","first-page":"556","article-title":"Algorithms for non-negative matrix factorization algorithms for non-negative matrix factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"13","author":"Lee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2016.7471631"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2017.7952155"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.1700814"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-022-09640-y"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/e24010055"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2010.5495662"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326383"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-394"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.901310"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/1268779"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1561\/9781601981219"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2006-23"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326122"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.11.001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2009.5346527"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495323"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-008-0274-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2009.5306201"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1201\/b19706-5"},{"key":"ref49","first-page":"1963","article-title":"Learning spectral clustering, with application to speech separation","volume":"7","author":"Bach","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-013-1439-2"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2010633"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-726"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2012-429"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.09.002"},{"key":"ref56","first-page":"224","article-title":"Cocktail party processing via structured prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"1","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854299"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462116"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2001.941023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3099291"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015050"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1121\/1.408434"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.832812"},{"key":"ref72","volume-title":"An Introduction to the Psychology of Hearing","author":"Moore","year":"2012"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2001.938830"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-22794-6_12"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2536478"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2019.2908760"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178061"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1992-277"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2821"},{"key":"ref83","article-title":"Voice separation with an unknown number of multiple speakers","author":"Nachmani","year":"2020","journal-title":"arXiv:2003.01531"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref85","doi-asserted-by":"crossref","DOI":"10.6028\/NIST.IR.4930","volume-title":"DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM. NIST speech disc 1-1.1","volume":"93","author":"Garofolo","year":"1993"},{"key":"ref86","author":"Kabal","year":"2002","journal-title":"TSP speech database"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCT46805.2019.8947242"},{"key":"ref88","volume-title":"Speech Separation Challenge","author":"Cooke","year":"2006"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.05.005"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref91","volume-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2951894"},{"key":"ref93","article-title":"LibriMix: An open-source dataset for generalizable speech separation","author":"Cosentino","year":"2020","journal-title":"arXiv:2005.11262"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-149"},{"key":"ref95","article-title":"An efficient encoder\u2013decoder architecture with top-down attention for speech separation","author":"Li","year":"2022","journal-title":"arXiv:2209.15200"},{"key":"ref96","volume-title":"SUPERSEDED\u2014CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref97","first-page":"190","article-title":"Training and analyzing deep recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hermans"},{"key":"ref98","first-page":"1","article-title":"How to construct deep recurrent neural networks","volume-title":"Proc. 2nd Int. Conf. Learn. Represent.","author":"Pascanu"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952157"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1121\/1.3184603"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2687829"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2018.2795749"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2997871"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2018.8462507"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1550"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1940"},{"key":"ref107","article-title":"Spatial and spectral deep attention fusion for multi-channel speech separation using deep embedding features","author":"Fan","year":"2020","journal-title":"arXiv:2002.01626"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706611"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-216"},{"key":"ref110","first-page":"477","article-title":"Singing-voice separation from monaural recordings using deep recurrent neural networks","volume-title":"Proc. 15th Int. Soc. Music Inf. Retr. Conf.","author":"Sen Huang"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2982029"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462505"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1150"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461477"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054572"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3007779"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2019.2892241"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683231"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1629"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-2290"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3029704"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3176003"},{"key":"ref128","article-title":"CasNet: Investigating channel robustness for speech separation","author":"Wang","year":"2022","journal-title":"arXiv:2210.15370"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383464"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3193245"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/mlsp49062.2020.9231900"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_53"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413837"},{"key":"ref135","first-page":"22509","article-title":"Speech separation using an asynchronous fully recurrent convolutional neural network","volume-title":"Proc. NeurIPS","volume":"34","author":"Hu"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/450"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2181"},{"key":"ref138","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683169"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref143","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv:1803.01271"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683634"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref148","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10011434.pdf?arnumber=10011434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T03:05:33Z","timestamp":1707447933000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10011434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":149,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3235010","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}