{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T12:50:26Z","timestamp":1780318226767,"version":"3.54.1"},"reference-count":74,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["61971352"],"award-info":[{"award-number":["61971352"]}],"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":["61862043"],"award-info":[{"award-number":["61862043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007834","name":"Natural Science Foundation of Ningbo","doi-asserted-by":"publisher","award":["2021J048"],"award-info":[{"award-number":["2021J048"]}],"id":[{"id":"10.13039\/100007834","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007834","name":"Natural Science Foundation of Ningbo","doi-asserted-by":"publisher","award":["2021J049"],"award-info":[{"award-number":["2021J049"]}],"id":[{"id":"10.13039\/100007834","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Jiangxi Province in China","award":["20204BC J22011"],"award-info":[{"award-number":["20204BC J22011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3199109","type":"journal-article","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T19:49:17Z","timestamp":1660592957000},"page":"5800-5812","source":"Crossref","is-referenced-by-count":29,"title":["Look&listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5180-1295","authenticated-orcid":false,"given":"Junwen","family":"Xiong","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6356-8360","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9690-7026","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0541-8612","authenticated-orcid":false,"given":"Wei","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5013-2501","authenticated-orcid":false,"given":"Yufei","family":"Zha","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301977"},{"key":"ref56","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref15","article-title":"Naver at activitynet challenge 2019–task B active speaker detection (AVA)","author":"chung","year":"2019"},{"key":"ref59","article-title":"WaveNet: A generative model for raw audio","author":"oord","year":"0","journal-title":"Proc 9th ISCA Speech Synth Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref55","first-page":"1","article-title":"Ictcas-ucas-tal submission to the ava-activespeaker task at activitynet challenge 2021","volume":"1","author":"zhang","year":"2021","journal-title":"ActivityNet Large Scale Activity Recognition Challenge"},{"key":"ref10","first-page":"1193","article-title":"How to design a three-stage architecture for audio-visual active speaker detection in the wild","author":"k\u00f6p\u00fckl\u00fc","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref16","first-page":"1","article-title":"Multi-task learning for audio-visual active speaker detection","author":"zhang","year":"0","journal-title":"Proc ActivityNet Large-Scale Activity Recognit Challenge"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1955"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20111"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2822907"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2624140"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2852750"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2005.04.022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137988"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2016.7906033"},{"key":"ref9","first-page":"3927","article-title":"Is someone speaking? exploring long-term temporal features for audio-visual active speaker detection","author":"tao","year":"0","journal-title":"Proc 29th ACM Int Conf Multimedia"},{"key":"ref4","first-page":"12462","article-title":"Active speakers in context","author":"alc\u00e1zar","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.5.001749"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0710826105"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1964?1973,","DOI":"10.1162\/jocn.2007.19.12.1964","article-title":"Neural correlates of multisensory integration of ecologically valid audiovisual events","volume":"19","author":"stekelenburg","year":"2007","journal-title":"J Cogn Neurosci"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref35","article-title":"Crossmodal learning for audio-visual speech event localization","author":"sharma","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.07.003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3675-12.2013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref30","article-title":"Audio visual speech recognition","author":"neti","year":"2000"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1573"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2976493"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-6123(06)55014-9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2004.02.002"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74936-3_22"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00114"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00238"},{"key":"ref24","first-page":"2549","article-title":"A simple but efficient real-time voice activity detection algorithm","author":"moattar","year":"0","journal-title":"Proc 17th Eur Signal Process Conf"},{"key":"ref68","first-page":"265","article-title":"MAAS: Multi-modal assignation for active speaker detection","author":"alc\u00e1zar","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414263"},{"key":"ref67","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535357"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305632"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCNT51525.2021.9580127"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref64","article-title":"MUSAN: A music, speech, and noise corpus","author":"snyder","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414133"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1142\/S021946780100027X"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2269314"},{"key":"ref27","first-page":"8","article-title":"The enterface'05 audio-visual emotion database","author":"martin","year":"0","journal-title":"Proceedings of the 22nd International Conference on Data Engineering Workshops"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3032037"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref62","article-title":"Lrs3-ted: A large-scale dataset for visual speech recognition","author":"afouras","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09858007.pdf?arnumber=9858007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:59:58Z","timestamp":1701115198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9858007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3199109","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}