{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:04:21Z","timestamp":1753272261271,"version":"3.37.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2018,7,1]],"date-time":"2018-07-01T00:00:00Z","timestamp":1530403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"EPSRC Programme Grant S3A: Future Spatial Audio for an Immersive Listener Experience at Home","award":["EP\/L000539\/1"],"award-info":[{"award-number":["EP\/L000539\/1"]}]},{"name":"BBC as part of the BBC Audio Research Partnership"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1109\/tmm.2017.2777671","type":"journal-article","created":{"date-parts":[[2017,11,24]],"date-time":"2017-11-24T19:04:50Z","timestamp":1511550290000},"page":"1767-1780","source":"Crossref","is-referenced-by-count":15,"title":["Multiple Speaker Tracking in Spatial Audio via PHD Filtering and Depth-Audio Fusion"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0778-2992","authenticated-orcid":false,"given":"Qingju","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8393-5703","authenticated-orcid":false,"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teofilo","family":"de Campos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip J. B.","family":"Jackson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Hilton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2015.10.003"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1115\/1.4025810"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2005.1561884"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2003.1261119"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2012.6180911"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2013.52"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11900-7_40"},{"year":"0","key":"ref36","article-title":"More about kinect sensor placement"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881190"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2012.6178085"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130370"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095075"},{"key":"ref29","first-page":"3838","article-title":"People detection in RGB-D data","author":"arras","year":"0","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref2","article-title":"Production and reproduction of program\n material for a variety of spatial audio formats","author":"francombe","year":"0","journal-title":"Proc 138th Audio Eng Soc Conv (e-Brief)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2264784"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937600"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383345"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.881678"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2377515"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2301977"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1121241.1121310"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2599150"},{"key":"ref50","article-title":"Audio-visual speaker diarization based on\n spatiotemporal Bayesian fusion","author":"gebru","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70834"},{"journal-title":"Elementary Statistics","year":"1976","author":"hoel","key":"ref53"},{"article-title":"DARPA TIMIT acoustic-phonetic continuous\n speech corpus CD-ROM. NIST speech disc 1-1.1","year":"1993","author":"garofolo","key":"ref52"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/ASP\/2006\/17021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2178402"},{"year":"0","key":"ref40","article-title":"Skeletal tracking with multiple kinect sensors"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-007-0017-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.08.009"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.008"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543447"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2012.24"},{"year":"2015","key":"ref17","article-title":"Kinect for Windows"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126310"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.877658"},{"key":"ref3","article-title":"On object-based audio with reverberation","author":"coleman","year":"0","journal-title":"Proc 60th Int Conf Audio Eng Soc"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670953"},{"year":"2015","key":"ref5","article-title":"PhaseSpace: Impulse motion capture"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2390044"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.2000.0870"},{"key":"ref49","first-page":"1775","article-title":"Measurement\n and analysis of a spatially sampled binaural room impulse response dataset","author":"satongar","year":"0","journal-title":"Proc 10th Int Congr Sound Vib"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.940294"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471928"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2010.5595616"},{"article-title":"Binaural room impulse response measurements","year":"2011","author":"hummersone","key":"ref48"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162830"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.97"},{"year":"0","key":"ref41","article-title":"Skeleton tracking with multiple kinect sensors"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2001379"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.886266"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8386723\/08119824.pdf?arnumber=8119824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:23:08Z","timestamp":1642004588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8119824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":54,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2777671","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}