{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:32:41Z","timestamp":1768073561085,"version":"3.49.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61671095"],"award-info":[{"award-number":["61671095"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61702065"],"award-info":[{"award-number":["61702065"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61701067"],"award-info":[{"award-number":["61701067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771085"],"award-info":[{"award-number":["61771085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201113"],"award-info":[{"award-number":["62201113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014886","name":"Chongqing Municipal Key Laboratory of Signal and Information Processing","doi-asserted-by":"publisher","award":["CSTC2009CA2003"],"award-info":[{"award-number":["CSTC2009CA2003"]}],"id":[{"id":"10.13039\/501100014886","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing","doi-asserted-by":"publisher","award":["cstc2021jcyj-msxmX0836"],"award-info":[{"award-number":["cstc2021jcyj-msxmX0836"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Project of Chongqing Educational Commission","award":["KJ1600427"],"award-info":[{"award-number":["KJ1600427"]}]},{"name":"Research Project of Chongqing Educational Commission","award":["KJ1600429"],"award-info":[{"award-number":["KJ1600429"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3463411","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T18:01:14Z","timestamp":1726682474000},"page":"4647-4660","source":"Crossref","is-referenced-by-count":6,"title":["Audio-Visual Fusion With Temporal Convolutional Attention Network for Speech Separation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7411-9683","authenticated-orcid":false,"given":"Debang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2160-7701","authenticated-orcid":false,"given":"Tianqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3586-7969","authenticated-orcid":false,"given":"Mads Gr\u00e6sb\u00f8ll","family":"Christensen","sequence":"additional","affiliation":[{"name":"Audio Analysis Laboratory, CREATE, Aalborg University, Aalborg, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2844-5787","authenticated-orcid":false,"given":"Chen","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9947-9634","authenticated-orcid":false,"given":"Zeliang","family":"An","sequence":"additional","affiliation":[{"name":"School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1121\/1.1907229","article-title":"Experiments described herein are intended as a","volume":"25","author":"Cherry","year":"1953","journal-title":"J. Acoustical Soc. Amer."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSN.2017.8230274"},{"key":"ref4","volume-title":"Computational Auditory Scene Analysis Principles, Algorithms, and Applications","author":"Wang","year":"2006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-526"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853900"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853860"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2468583"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2352935"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3675-12.2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3109\/03005368709077786"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0004638"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462527"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2761539"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2853566"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2928140"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2835719"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1065"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.08.008"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.006"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.11.081"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3228537"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-49409-8_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.30"},{"key":"ref49","article-title":"Deep learning using rectified linear units (relu)","author":"Agarap","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref51","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref57","article-title":"Musan: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref58","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref62","first-page":"2579","article-title":"Visualizing data using t-Sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10683978.pdf?arnumber=10683978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:51:23Z","timestamp":1732665083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10683978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3463411","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}