{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:50:56Z","timestamp":1790776256226,"version":"4.1.0"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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 Trans. Multimedia"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/tmm.2019.2902489","type":"journal-article","created":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T20:00:26Z","timestamp":1551470426000},"page":"2576-2588","source":"Crossref","is-referenced-by-count":55,"title":["Multi-Speaker Tracking From an Audio\u2013Visual Sensing Device"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9511-6713","authenticated-orcid":false,"given":"Xinyuan","family":"Qian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4146-3071","authenticated-orcid":false,"given":"Alessio","family":"Brutti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4793-4276","authenticated-orcid":false,"given":"Oswald","family":"Lanz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0879-0548","authenticated-orcid":false,"given":"Maurizio","family":"Omologo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Cavallaro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2405475"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.96"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952686"},{"key":"ref32","first-page":"1","article-title":"Three dimensional object tracking based on audiovisual fusion using particle swarm optimization","author":"keyrouz","year":"0","journal-title":"Proc Int Conf Inf Fusion"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-69568-4_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1088463.1088477"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.60"},{"key":"ref36","author":"brandstein","year":"1995","journal-title":"A framework for speech source localization using sensor arrays"},{"key":"ref35","first-page":"898","article-title":"Audio–visual person tracking with a mobile robot","author":"fritsch","year":"0","journal-title":"Proc Int Conf Intell Auton Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301977"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/JOE.1983.1145560"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1979.1102177"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/11744085_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_17"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1206512"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/147495"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/34.888718"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.177"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/1486525.1486527"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833032"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1002\/9780470974377"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1155\/ASP\/2006\/26503"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/89.568735"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2794780"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777671"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7"},{"key":"ref25","first-page":"1","article-title":"Acoustic transduction","author":"omologo","year":"1998","journal-title":"Spoken Dialogue with Computers"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1975.1055330"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698614"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.232"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3437-9"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2014.09.004"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366096"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.330"},{"key":"ref54","author":"hartley","year":"2003","journal-title":"Multiple View Geometry in Computer Vision"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2057231"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206058"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881678"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-012-0111-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2648793"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2007.893340"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-0027-7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.159"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960384"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2008.2001429"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.06.005"},{"key":"ref4","first-page":"974","article-title":"A joint particle filter to track the position and head orientation of people using audio visual cues","author":"brutti","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSC.2007.4357521"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/EVENT.2001.938862"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1049\/cp.2012.0410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057890"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICMT.2011.6002028"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2599150"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.922063"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461323"},{"key":"ref45","article-title":"AV16.3: An audio–visual corpus for speaker localization and tracking","author":"lathoud","year":"2004","journal-title":"Machine Learning for Multimodal Interaction"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461791"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415697"},{"key":"ref42","article-title":"Surveillance performance evaluation initiative (SPEVI): Audiovisual people dataset","author":"taj","year":"2007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1452392.1452414"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-007-9054-4"},{"key":"ref43","first-page":"3","article-title":"Announcing the AMI meeting corpus","volume":"11","author":"carletta","year":"2006","journal-title":"ELRA Newsletter"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8846791\/08656587.pdf?arnumber=8656587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:47:06Z","timestamp":1657745226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8656587\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":69,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2902489","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}