{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:15:55Z","timestamp":1778080555447,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/50008\/2020"],"award-info":[{"award-number":["UIDB\/50008\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia (FCT) Doctoral","doi-asserted-by":"publisher","award":["2020.09847.BD"],"award-info":[{"award-number":["2020.09847.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia (FCT) Doctoral","doi-asserted-by":"publisher","award":["2021.04905.BD"],"award-info":[{"award-number":["2021.04905.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia (FCT) Doctoral","doi-asserted-by":"publisher","award":["CENTRO-01-0145-FEDER-000019"],"award-info":[{"award-number":["CENTRO-01-0145-FEDER-000019"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Biom. Behav. Identity Sci."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tbiom.2024.3412821","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:41:17Z","timestamp":1718131277000},"page":"61-70","source":"Crossref","is-referenced-by-count":7,"title":["WASD: A Wilder Active Speaker Detection Dataset"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9563-8039","authenticated-orcid":false,"given":"Tiago","family":"Roxo","sequence":"first","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3995-4621","authenticated-orcid":false,"given":"Joana Cabral","family":"Costa","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8221-0666","authenticated-orcid":false,"given":"Pedro R. M.","family":"In\u00e1cio","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2551-8570","authenticated-orcid":false,"given":"Hugo","family":"Proen\u00e7a","sequence":"additional","affiliation":[{"name":"Instituto de Telecomunicações, University of Beira Interior, Covilhã, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv:1809.00496"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820780"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"ref10","article-title":"Naver at activitynet challenge 2019\u2014Task B active speaker detection (AVA)","author":"Chung","year":"2019","journal-title":"arXiv:1906.10555"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3116"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref16","first-page":"1","article-title":"Lip reading in profile","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Chung"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-62"},{"key":"ref19","article-title":"EasyCom: An augmented reality dataset to support algorithms for easy communication in noisy environments","author":"Donley","year":"2021","journal-title":"arXiv:2107.04174"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.92"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.04.018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref24","first-page":"1102","article-title":"The REPERE corpus: A multimodal corpus for person recognition","volume-title":"Proc. 8th Int. Conf. Lang. Resour. Eval. (LREC)","author":"Giraudel"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/1027933.1027972"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806293"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2041"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00123"},{"key":"ref32","article-title":"CrowdPose: Efficient crowded scenes pose estimation and a new benchmark","author":"Li","year":"2018","journal-title":"arXiv:1812.00324"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535357"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745028"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061800"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10471"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3157857"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.251"},{"key":"ref45","volume-title":"OpenCV\/CVAT: V1.1.0.","author":"Sekachev","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1573"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","article-title":"LoCoNet: Long-short context network for active speaker detection","author":"Wang","year":"2023","journal-title":"arXiv:2301.08237"},{"key":"ref51","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. J. Int. Conf. Learn. Represent. (ICLR)","author":"Welling"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"ref53","first-page":"1","article-title":"Pose Flow: Efficient online pose tracking","volume-title":"Proc. BMVC","author":"Xiu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref55","first-page":"1","article-title":"Multi-task learning for audio-visual active speaker detection","volume-title":"Proc. ActivityNet Large-Scale Activity Recognit. Chall.","author":"Zhang"}],"container-title":["IEEE Transactions on Biometrics, Behavior, and Identity Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8423754\/10816731\/10554644.pdf?arnumber=10554644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,28]],"date-time":"2024-12-28T06:03:54Z","timestamp":1735365834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10554644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":55,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tbiom.2024.3412821","relation":{},"ISSN":["2637-6407"],"issn-type":[{"value":"2637-6407","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}