{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T10:57:56Z","timestamp":1768474676079,"version":"3.49.0"},"reference-count":79,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017538","name":"Zhejiang Province Ten Thousand Talents Program","doi-asserted-by":"publisher","award":["ID 2019R51010"],"award-info":[{"award-number":["ID 2019R51010"]}],"id":[{"id":"10.13039\/501100017538","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Lab Postdoctoral start-up fund","award":["115002-UB2107QJ"],"award-info":[{"award-number":["115002-UB2107QJ"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20488"],"award-info":[{"award-number":["U21A20488"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3267668","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T18:07:06Z","timestamp":1681754826000},"page":"45140-45153","source":"Crossref","is-referenced-by-count":2,"title":["Efficient Audiovisual Fusion for Active Speaker Detection"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7472-4007","authenticated-orcid":false,"given":"Fiseha B.","family":"Tesema","sequence":"first","affiliation":[{"name":"Interdisciplinary Innovation Research Institute, Zhejiang Lab, Zhongtai, Yuhang, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7626-1077","authenticated-orcid":false,"given":"Jason","family":"Gu","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Dalhousie University, Halifax, NS, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0828-7486","authenticated-orcid":false,"given":"Wei","family":"Song","sequence":"additional","affiliation":[{"name":"Interdisciplinary Innovation Research Institute, Zhejiang Lab, Zhongtai, Yuhang, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqiang","family":"Zhu","sequence":"additional","affiliation":[{"name":"Interdisciplinary Innovation Research Institute, Zhejiang Lab, Zhongtai, Yuhang, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheyuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Interdisciplinary Innovation Research Institute, Zhejiang Lab, Zhongtai, Yuhang, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88693-8_12"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref12","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462375"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953097"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.04.018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.02.009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1244"},{"key":"ref52","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref55","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"arXiv 1703 03130"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref54","article-title":"A deep reinforced model for abstractive summarization","author":"paulus","year":"2017","journal-title":"arXiv 1705 04304"},{"key":"ref17","first-page":"12465","article-title":"Active speakers in context","author":"alc\u00e1zar","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054760"},{"key":"ref18","article-title":"Naver at ActivityNet challenge 2019—Task B active speaker detection (AVA)","author":"chung","year":"2019","journal-title":"arXiv 1906 10555"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref50","first-page":"814","article-title":"FaceSync: A linear operator for measuring synchronization of video facial images and audio tracks","volume":"13","author":"slaney","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45113-7_48"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/GLU.2017-10"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2006.285274"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1631272.1631301"},{"key":"ref42","first-page":"22","article-title":"Look who’s talking: Visual identification of the active speaker in multi-party human–robot interaction","author":"stefanov","year":"2016","journal-title":"Proc 2nd Workshop Adv Social Signal Process Multimodal Interact"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2013.171"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.2009262"},{"key":"ref49","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2007344"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2013.7029977"},{"key":"ref9","first-page":"1589","article-title":"Look who’s talking: Speaker detection using video and audio correlation","author":"cutler","year":"2000","journal-title":"Proc IEEE Int Conf Multimedia Expo (ICME) Latest Adv Fast Changing World Multimedia"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2016.7906033"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/mti3040070"},{"key":"ref6","first-page":"151","article-title":"Voice activity detection based on fusion of audio and visual information","author":"takeuchi","year":"2009","journal-title":"Proc AVSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/274644.274668"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2927941"},{"key":"ref35","author":"chollet","year":"2015","journal-title":"Keras"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1076"},{"key":"ref34","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9005997"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00483"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993172"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1117\/12.2643881"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2310"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053171"},{"key":"ref39","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305632"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00123"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/11965152_32"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.10.110"},{"key":"ref23","first-page":"402","article-title":"Robust speaker segmentation for meetings: The ICSI-SRI spring 2005diarization system","author":"anguera","year":"2005","journal-title":"Proc Int Workshop Mach Learn Multimodal Interact"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.92"},{"key":"ref25","article-title":"Putting a face to the voice: Fusing audio and visual signals across a video to determine speakers","author":"hoover","year":"2017","journal-title":"arXiv 1706 00079"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3070138"},{"key":"ref20","article-title":"You said that?","author":"chung","year":"2017","journal-title":"arXiv 1705 02966"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8843186"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/76.718513"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref66","article-title":"Advances and challenges in deep lip reading","author":"oghbaie","year":"2021","journal-title":"arXiv 2110 07879"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-019-01630-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.251"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820780"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2172"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-4"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10103538.pdf?arnumber=10103538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:41:54Z","timestamp":1685382114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10103538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3267668","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}