{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:18:57Z","timestamp":1776889137858,"version":"3.51.2"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2014,1]]},"DOI":"10.1109\/taslp.2013.2285474","type":"journal-article","created":{"date-parts":[[2013,12,4]],"date-time":"2013-12-04T19:47:51Z","timestamp":1386186471000},"page":"217-227","source":"Crossref","is-referenced-by-count":128,"title":["A Study of the Cosine Distance-Based Mean Shift for Telephone Speech Diarization"],"prefix":"10.1109","volume":"22","author":[{"given":"Mohammed","family":"Senoussaoui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Kenny","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Themos","family":"Stafylakis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre","family":"Dumouchel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J R Statist Soc Ser B (Methodol )"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937550"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-53","article-title":"Analysis of i-vector length normalization in Gaussian-PLDA speaker recognition systems","author":"garcia-romero","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref10","article-title":"Mean shift algorithm for exponential families with applications to speaker clustering","author":"stafylakis","year":"2012","journal-title":"IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639164"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref13","article-title":"Cosine similarity scoring without score normalization techniques","author":"dehak","year":"2010","journal-title":"Proc IEEE Odyssey Workshop"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947363"},{"key":"ref15","article-title":"An i-vector extractor suitable for speaker recognition with both microphone and telephone speech","author":"senoussaoui","year":"2010","journal-title":"Proc Odyssey Speaker Lang Recognition Workshop"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"945","DOI":"10.21437\/Interspeech.2011-383","article-title":"Exploiting intra-conversation variability for speaker diarization","author":"shum","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-163","article-title":"On the use of spectral and iterative methods for speaker diarization","author":"shum","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.2001-246","article-title":"Speaker recognition in a multi-speaker environment","author":"martin","year":"2001","journal-title":"Proc EUROSPEECH"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-654","article-title":"Unsupervised segmentation and verification of multi-speaker conversational speech","author":"dalmasso","year":"2005","journal-title":"Proc INTERSPEECH"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2081790"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238382"},{"key":"ref3","author":"valente","year":"2005","journal-title":"Variational Bayesian methods for audio indexing"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1195991"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1975.1055330"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.11.017"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2007.09.009"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/34.1000236"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/34.400568"},{"key":"ref2","first-page":"645","article-title":"Clustering via the bayesian information criterion with applications in speech recognition","volume":"2","author":"chen","year":"1998","journal-title":"Proc ICASSP"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344136"},{"key":"ref9","article-title":"Speaker clustering via the mean shift algorithm","author":"stafylakis","year":"2010","journal-title":"Proc of the IEEE Odyssey Speaker and Language Recognition Workshop"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518564"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"857","DOI":"10.21437\/Interspeech.2011-328","article-title":"Language recognition via i-vectors and dimensionality reduction","author":"dehak","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref21","author":"vaquero avil\ufffds-casco","year":"2011","journal-title":"Robust diarization for speaker characterization Diarizacion robusta para caracterizacion de locutores)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.174"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-329","article-title":"Language recognition in iVectors space","author":"martinez","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.840940"},{"key":"ref25","author":"kenny","year":"2006","journal-title":"?Joint factor analysis of speaker and session variability Theory and algorithms ?"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/6663728\/06633085.pdf?arnumber=6633085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T01:48:08Z","timestamp":1746064088000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6633085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,1]]},"references-count":33,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2013.2285474","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,1]]}}}