{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T20:34:27Z","timestamp":1767990867670,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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":[{"name":"FD-fAbrICS: Joint Lab for FD-SOI Always-on Intelligent & Connected Systems","award":["I2001E0053"],"award-info":[{"award-number":["I2001E0053"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["ZDSYS20230626091302006"],"award-info":[{"award-number":["ZDSYS20230626091302006"]}]},{"name":"Shenzhen Science and Technology Research Fund"},{"name":"Fundamental Research Key Project","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521791","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:32:25Z","timestamp":1735155145000},"page":"2362-2373","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Real-World Active Speaker Detection With Multi-Modal Extraction Pre-Training"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0021-5661","authenticated-orcid":false,"given":"Ruijie","family":"Tao","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9511-6713","authenticated-orcid":false,"given":"Xinyuan","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Science and Technology Beijing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1332-3357","authenticated-orcid":false,"given":"Rohan Kumar","family":"Das","sequence":"additional","affiliation":[{"name":"Fortemedia, Singapore, Singapore"}]},{"given":"Xiaoxue","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9372-3133","authenticated-orcid":false,"given":"Jiadong","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268568"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447160"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535357"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548027"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00517"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29882"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref17","first-page":"1298","article-title":"DATA2VEC: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref19","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shi","year":"2022"},{"key":"ref20","first-page":"3927","article-title":"Is someone speaking? Exploring long-term temporal features for audio-visual active speaker detection","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Tao","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003983"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3205759"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature11020"},{"issue":"1","key":"ref26","first-page":"117","article-title":"The cocktail party phenomenon: A review of research on speech intelligibility in multiple-talker conditions","volume":"86","author":"Bronkhorst","year":"2000","journal-title":"Acta Acustica United Acustica"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref29","article-title":"Naver at activitynet challenge","author":"Chung","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00985"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746991"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-574"},{"key":"ref35","first-page":"1193","article-title":"How to design a three-stage architecture for audio-visual active speaker detection in the wild","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Kpkl","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1049\/ep.1987.0120"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2041"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref50","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01747"},{"key":"ref52","article-title":"Multi-task learning for audio-visual active speaker detection","volume-title":"Proc. ActivityNet Large-Scale Activity Recognit. Challenge","author":"Zhang","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00033"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-80"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3267269"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref57","article-title":"UniCon+: ICTCAS-UCAS submission to the AVA-Activespeaker task at activitynet challenge 2022","author":"Zhang","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55214.2022.9943352"},{"key":"ref59","article-title":"Lip movements information disentanglement for lip sync","author":"Wang","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30642-7_5"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3007350"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00238"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7424-8"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00357"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814693.pdf?arnumber=10814693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:47:43Z","timestamp":1747158463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521791","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}