{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T11:33:02Z","timestamp":1778326382693,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446460","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8100-8104","source":"Crossref","is-referenced-by-count":4,"title":["GLMB 3D Speaker Tracking with Video-Assisted Multi-Channel Audio Optimization Functions"],"prefix":"10.1109","author":[{"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[{"name":"University of Science and Technology Beijing,School of Computer and Communication Engineering,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexu","family":"Pan","sequence":"additional","affiliation":[{"name":"National University of Singapore,Institute of Data Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of New South Wales,School of Electrical Engineering and Telecommunications,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kainan","family":"Chen","sequence":"additional","affiliation":[{"name":"Eigenspace GmbH,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoufeng","family":"Lin","sequence":"additional","affiliation":[{"name":"Curtin University,Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1513"},{"key":"ref2","first-page":"3927","article-title":"Is someone speaking? exploring long-term temporal features for audio-visual active speaker detection","volume-title":"Proc. of the Int. Conf. on Multimedia","author":"Tao"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3226330"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803117"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.922063"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3092959"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2005.1540183"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461323"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref15","volume-title":"Spoken Dialogue with Computers","author":"Renato","year":"1998"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.877658"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940294"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2003.818112"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461605"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAIS.2016.7822442"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2259822"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2014.2364014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7_8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30568-2_16"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446460.pdf?arnumber=10446460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:17:24Z","timestamp":1722575844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446460","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}