{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T18:51:24Z","timestamp":1735584684570},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science & Technology Fundamental Research Programs","award":["JCYJ20170817160058246","JCYJ20180507182908274"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/jstsp.2020.2980956","type":"journal-article","created":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T02:43:55Z","timestamp":1584413035000},"page":"530-541","source":"Crossref","is-referenced-by-count":62,"title":["Multi-Modal Multi-Channel Target Speech Separation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-1861-9170","authenticated-orcid":false,"given":"Rongzhi","family":"Gu","sequence":"first","affiliation":[]},{"given":"Shi-Xiong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Lianwu","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9999-6140","authenticated-orcid":false,"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0520-6844","authenticated-orcid":false,"given":"Dong","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521243"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref31","first-page":"639","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref30","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2901664"},{"key":"ref36","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461816"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461930"},{"key":"ref28","first-page":"2655","article-title":"Speaker-aware neural network based beamformer for speaker extraction in speech mixtures","author":"zmolikova","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2266"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682245"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015050"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1908248"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928140"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461639"},{"key":"ref23","first-page":"558","article-title":"Multi-channel overlapped speech recognition with location guided speech extraction network","author":"chen","year":"0","journal-title":"Proc IEEE Spoken Lang Technol Workshop"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682470"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref51","first-page":"1131","article-title":"Methodologies for the evaluation of speaker diarization and automatic speech recognition in the presence of overlapping speech","author":"galibert","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref40","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc IEEE Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref13","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"0","journal-title":"Proc Asian Conf Comput Vision"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1205"},{"key":"ref17","first-page":"8","article-title":"Learning speaker representation for neural network based multichannel speaker extraction","author":"\u017emol\u00edkov\u00e1","year":"0","journal-title":"Proc IEEE Autom Speech Recognit Understanding Workshop"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1101"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/JSTSP.2019.2922820","article-title":"Speakerbeam: Speaker aware neural network for target speaker extraction in speech mixtures","volume":"13","author":"\u017emol\u00edkov\u00e1","year":"2019","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref9","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1121\/1.2936367"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3181"},{"key":"ref48","article-title":"Tasnet: Surpassing ideal time-frequency masking for speech separation","author":"luo","year":"2018"},{"key":"ref47","article-title":"A large-scale audio-visual corpus for multimodal speaker diarization, speech separation and recognition","year":"0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178829"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2831456"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref43","article-title":"Factorized deep neural networks for adaptive speech recognition","author":"yu","year":"0","journal-title":"Proc Int Workshop Statistical Mach Learn Speech Process"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9126272\/09036927.pdf?arnumber=9036927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:08:26Z","timestamp":1651079306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9036927\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":51,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2020.2980956","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}