{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:44:47Z","timestamp":1784335487243,"version":"3.55.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T00:00:00Z","timestamp":1443657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Basic Science Research Program, National Research Foundation of Korea (NRF),","award":["2010-0020163"],"award-info":[{"award-number":["2010-0020163"]}]},{"DOI":"10.13039\/501100002635","name":"Inha University","doi-asserted-by":"crossref","award":["INHA-51376"],"award-info":[{"award-number":["INHA-51376"]}],"id":[{"id":"10.13039\/501100002635","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2015,10]]},"DOI":"10.1109\/tmm.2015.2463722","type":"journal-article","created":{"date-parts":[[2015,8,3]],"date-time":"2015-08-03T18:28:32Z","timestamp":1438626512000},"page":"1694-1705","source":"Crossref","is-referenced-by-count":36,"title":["Multimodal Multi-Channel On-Line Speaker Diarization Using Sensor Fusion Through SVM"],"prefix":"10.1109","volume":"17","author":[{"given":"Vicente","family":"Peruffo Minotto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Rosito Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1177\/1094342012452166"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430196"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.113"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2007.4393034"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IranianCEE.2013.6599672"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISTEL.2012.6483115"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.11.002"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318478"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.01.008"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SIU.2013.6531416"},{"key":"ref34","first-page":"v3?582","article-title":"Identification of simultaneous speakers","volume":"3","author":"tsai","year":"2010","journal-title":"Proc 2nd Int Conf Comput Eng Technol"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iCECE.2010.310"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-3-642-28661-2_5","volume":"411","author":"shotton","year":"2013","journal-title":"Machine Learning for Computer Vision"},{"key":"ref61","first-page":"4349","article-title":"Localization of multiple speakers based on a two step acoustic map analysis","author":"brutti","year":"2008","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2160167"},{"key":"ref64","author":"quinlan","year":"1993","journal-title":"C4 5 Programs for Machine Learning"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.07.011"},{"key":"ref65","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":"ref66","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5496133"},{"key":"ref67","first-page":"469","article-title":"Face recognition with local binary patterns","volume":"3021","author":"ahonen","year":"2004","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1991.139758"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/34.598228"},{"key":"ref2","author":"rabiner","year":"1993","journal-title":"Fundamentals of speech recognition"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2006.10.019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661327"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430197"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1322192.1322254"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"363","DOI":"10.21437\/Interspeech.2008-149","article-title":"Improved novelty detection for online GMM-based speaker diarization","author":"markov","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref23","first-page":"233","article-title":"Towards audio-visual on-line diarization of participants in group meetings","author":"hung","year":"2008","journal-title":"Proc Eur Conf Comput Vis Workshop Multi-Camera Multi-Modal Sensor Fusion"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2011.5942417"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.21437\/Interspeech.2010-700","article-title":"A hybrid approach to online speaker diarization","author":"vaquero","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref50","author":"ahlberg","year":"2001","journal-title":"?Candide-3?An updated parameterised face ?"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2009.41"},{"key":"ref59","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 IEEE Int Conf Conf Acoust Speech Signal Process"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366632"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/89.848229"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/97.736233"},{"key":"ref55","author":"rabiner","year":"1978","journal-title":"Digital Processing of Speech Signals"},{"key":"ref54","first-page":"1","article-title":"A visual voice activity detection method with adaboosting","author":"liu","year":"2011","journal-title":"Proc Sensor Signal Process Defence"},{"key":"ref53","first-page":"2409","article-title":"Two novel visual voice activity detectors based on appearance models and retinal filltering","author":"aubrey","year":"2007","journal-title":"Proc 15th Eur Signal Process Conf"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2012.2237379"},{"key":"ref10","first-page":"1","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"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2009.5201171"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/11677482_34"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960522"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2050519"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1163","DOI":"10.21437\/Interspeech.2009-338","article-title":"Fusing audio and video information for online speaker diarization","author":"schmalenstroeer","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.47"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2233724"},{"key":"ref17","first-page":"1477","article-title":"An open-source state-of-the-art toolbox for broadcast news diarization","author":"rouvier","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"2170","DOI":"10.21437\/Interspeech.2012-579","article-title":"Diartk: An open source toolkit for research in multistream speaker diarization and its application to meetings recordings","author":"vijayasenan","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/978-3-540-68585-2_47","volume":"4625","author":"wooters","year":"2008","journal-title":"Multimodal Technologies for Perception of Humans"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-04619-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878261"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.05.002"},{"key":"ref8","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 Inf Fusion"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305632"},{"key":"ref9","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":"ref46","first-page":"1","article-title":"The AMI meeting corpus","author":"mccowan","year":"2005","journal-title":"Proc Int Conf Methods Tech Behav Res"},{"key":"ref45","first-page":"1","article-title":"The isl meeting corpus: The impact of meeting type on speech style","author":"burger","year":"2002","journal-title":"Proc INTERSPEECH"},{"key":"ref48","first-page":"1411","article-title":"The NIST meeting room pilot corpus","author":"garofolo","year":"2004","journal-title":"Proc LREC"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1007\/11677482_3","article-title":"The ami meeting corpus: A pre-announcement","author":"carletta","year":"2006","journal-title":"Proc 4th Int Conf Mach Learn Multimodal Interact"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851981"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704408026"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947336"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7268793\/07175035.pdf?arnumber=7175035","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,19]],"date-time":"2022-05-19T22:09:21Z","timestamp":1652998161000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7175035\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10]]},"references-count":70,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2015.2463722","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,10]]}}}