{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T02:12:27Z","timestamp":1774404747298,"version":"3.50.1"},"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"}],"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.2023.3346643","type":"journal-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T20:07:07Z","timestamp":1703534827000},"page":"984-995","source":"Crossref","is-referenced-by-count":7,"title":["Leveraging Visual Supervision for Array-Based Active Speaker Detection and Localization"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6279-6364","authenticated-orcid":false,"given":"Davide","family":"Berghi","sequence":"first","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Surrey, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7933-5935","authenticated-orcid":false,"given":"Philip J.B.","family":"Jackson","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, Surrey, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461267"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref6","first-page":"1","article-title":"Tools for 6-Dof immersive audio-visual content capture and production","volume-title":"Proc. IBC","author":"Schweiger","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref8","article-title":"Naver at ActivityNet Challenge 2019 - Task B Active speaker detection (AVA)","volume":"abs\/1906.10555","author":"Chung","year":"2019","journal-title":"CoRR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475275"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3565516.3565522"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733678"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871073"},{"key":"ref14","first-page":"117","article-title":"Towards speaker detection using lips movements for human-machine multiparty dialogue","volume-title":"Proc. Fonetik","author":"Haider","year":"2012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820780"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993172"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3474085"},{"key":"ref19","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref23","first-page":"2051","article-title":"Tracking sound sources for object-based spatial audio in 3D audio-visual production","volume-title":"Proc. Forum Acusticum","author":"Mohd Izhar","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777671"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.96"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366631"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178484"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.33682\/1xwd-5v76"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.33682\/4jhy-bj81"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053045"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413609"},{"key":"ref34","first-page":"11","article-title":"Event-independent network for polyphonic sound event localization and detection","volume-title":"Proc. Detection Classification Acoust. Scenes Events Workshop","author":"Cao","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413473"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3173054"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746132"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1400"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref40","first-page":"360","article-title":"Self-supervised generation of spatial audio for 360$^\\circ$ video","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Pedro Morgado","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00995"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00398"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref47","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2015"},{"key":"ref48","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","volume-title":"Proc. Neural Inf. Process. System","author":"Aytar","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240578"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01144"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_37"},{"key":"ref55","volume-title":"I now call it self-supervised learning","author":"LeCun","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01548-9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.09.072"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.30"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s13398-014-0173-7.2"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248185"},{"key":"ref61","article-title":"WebRTC","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1121\/1.1323720"},{"key":"ref65","first-page":"1","article-title":"Perceptual thresholds of audio-visual spatial coherence for a variety of audio-visual objects","volume-title":"Proc. Conf. Audio Virtual Augmented Reality","author":"Stenzel","year":"2018"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10373068.pdf?arnumber=10373068","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T00:28:33Z","timestamp":1705105713000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10373068\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3346643","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}