{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:56:44Z","timestamp":1764997004994},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2014,6,1]],"date-time":"2014-06-01T00:00:00Z","timestamp":1401580800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2014,6]]},"DOI":"10.1109\/tmm.2014.2305632","type":"journal-article","created":{"date-parts":[[2014,2,11]],"date-time":"2014-02-11T19:06:10Z","timestamp":1392145570000},"page":"1032-1044","source":"Crossref","is-referenced-by-count":33,"title":["Simultaneous-Speaker Voice Activity Detection and Localization Using Mid-Fusion of SVM and HMMs"],"prefix":"10.1109","volume":"16","author":[{"given":"Vicente P.","family":"Minotto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claudio R.","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1024691352"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2009.33"},{"key":"ref32","first-page":"121","article-title":"An iterative image registration technique with an application to stereo vision (darpa)","author":"lucas","year":"1981","journal-title":"Proc of the Image Understanding Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.07.011"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2009.0042"},{"key":"ref37","author":"rabiner","year":"1978","journal-title":"Digital Processing of Speech Signals"},{"key":"ref36","first-page":"593","article-title":"Good features to track","author":"shi","year":"1994","journal-title":"Proc 1994 IEEE Computer Society Conf Computer Vision and Pattern Recognition"},{"key":"ref35","article-title":"Pyramidal implementation of the Lucas Kanade feature tracker: Description of the algorithm","author":"bouguet","year":"2000"},{"key":"ref34","volume":"6","author":"farkas","year":"1994","journal-title":"Anthropometry of the Head and Face"},{"key":"ref28","article-title":"Voice activity detection based on fusion of audio and visual information","author":"takeuchi","year":"2009","journal-title":"Proc Int Conf Auditory-Visual Speech Process"},{"key":"ref27","author":"benesty","year":"2008","journal-title":"Microphone Array Signal Processing"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/5.168664"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.019"},{"key":"ref20","author":"dibiase","year":"2000","journal-title":"A High-Accuracy Low-Latency Technique for Talker Localization in Reverberant Environments Using Microphone Arrays"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iCECE.2010.310"},{"key":"ref21","first-page":"301","article-title":"A method for locating multiple sources from a frame of a large-aperture microphone array data without tracking","author":"do","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366632"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518618"},{"key":"ref26","article-title":"GPU-based approaches for real-time sound source localization using the SRP-PHAT algorithm","author":"peruffo minotto","year":"2012","journal-title":"Int J High Perform Comput Applicat"},{"key":"ref25","article-title":"A vectorized method for computationally eficient SRP-PHAT sound source localization","author":"lee","year":"2010","journal-title":"Proceedings of the Intl Workshop on Acoustic Echo and Noise Control"},{"key":"ref50","author":"huber","year":"2005","journal-title":"Robust Statistics"},{"key":"ref51","doi-asserted-by":"crossref","first-page":"3106","DOI":"10.21437\/Interspeech.2010-773","article-title":"Spectral entropy-based voice activity detector for videoconferencing systems","author":"lee","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref52","article-title":"A silence compression scheme for G.729 optimized for terminals conforming to Recommendation V.70, Annex B","year":"1996"},{"key":"ref10","first-page":"805","article-title":"An application of a particle filter to Bayesian multiple sound source tracking with audio and video information fusion","author":"asoh","year":"2004","journal-title":"Proc Int Conf Information Fusion (IF)"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"123","DOI":"10.21437\/Interspeech.2008-28","article-title":"Fusion of audio and video modalities for detection of acoustic events","author":"butko","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref40","first-page":"975","article-title":"Probability estimates for multi-class classification by pairwise coupling","volume":"5","author":"wu","year":"2004","journal-title":"J Mach Learn Res"},{"key":"ref12","article-title":"Using audio-visual features for robust voice activity detection in clean and noisy speech","author":"almajai","year":"2008","journal-title":"Proc 16th Eur Signal Process Conf (EUSIPCO 2008)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201171"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.848229"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2011.5942417"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.282037"},{"key":"ref18","article-title":"Multimodal speaker localization in a probabilistic framework","author":"gurban","year":"2006","journal-title":"Proc 14th Eur Signal Process Conf (EUSIPCO)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2011.0124"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164453"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5496183"},{"key":"ref5","first-page":"2","article-title":"Multi-speaker voice activity detection using ica and beampattern analysis","author":"maraboina","year":"2006","journal-title":"Proc Eur Signal Processing Conf (EUSIPCO)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5496133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISPACS.2010.5704658"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040525"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF01580735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198506881.001.0001"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719857"},{"key":"ref42","author":"johnson","year":"1993","journal-title":"Array Signal Processing - Concepts and Techniques"},{"key":"ref41","first-page":"1889","article-title":"Working set selection using second order information for training support vector machines","volume":"6","author":"fan","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2237379"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.09.002"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/6814813\/06737222.pdf?arnumber=6737222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,26]],"date-time":"2022-03-26T09:34:39Z","timestamp":1648287279000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6737222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,6]]},"references-count":52,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2014.2305632","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,6]]}}}