{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:35:06Z","timestamp":1784820906224,"version":"3.55.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2013,10,1]],"date-time":"2013-10-01T00:00:00Z","timestamp":1380585600000},"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. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1109\/tasl.2013.2264673","type":"journal-article","created":{"date-parts":[[2013,5,22]],"date-time":"2013-05-22T18:00:59Z","timestamp":1369245659000},"page":"2015-2028","source":"Crossref","is-referenced-by-count":133,"title":["Unsupervised Methods for Speaker Diarization: An Integrated and Iterative Approach"],"prefix":"10.1109","volume":"21","author":[{"given":"Stephen H.","family":"Shum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Najim","family":"Dehak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reda","family":"Dehak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James R.","family":"Glass","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1090\/conm\/026\/737400","article-title":"Extensions of Lipschitz mappings into a Hilbert space","volume":"26","author":"johnson","year":"1984","journal-title":"Contemp Math"},{"key":"ref38","article-title":"Construction of dependent Dirichlet processes based on Poisson processes","author":"lin","year":"2010","journal-title":"Proc NIPS"},{"key":"ref33","article-title":"On spectral clustering: Analysis and an algorithm","author":"ng","year":"2001","journal-title":"Proc NIPS"},{"key":"ref32","author":"beal","year":"2003","journal-title":"Variational algorithms for approximate Bayesian inference"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-45528-0"},{"key":"ref30","year":"2006","journal-title":"Diarization Error Rate (DER) Scoring Code"},{"key":"ref37","author":"johnson","year":"2010","journal-title":"PYHSMM A Python Library for Bayesian Inference in (HDP-)H(S)MMS"},{"key":"ref36","author":"khan","year":"2008","journal-title":"Variational Bayesian EM for Gaussian Mixture Models"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2003.1318476"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOAS395"},{"key":"ref40","article-title":"Principal component analysis with contaminated data: The high dimensional case","author":"xu","year":"2010","journal-title":"Proc COLT"},{"key":"ref11","article-title":"The hierarchical dirichlet process hidden semi-markov model","author":"johnson","year":"2010","journal-title":"Proc Conf Uncert Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/06-BA104"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2081790"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518564"},{"key":"ref15","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-383","article-title":"Exploiting intra-conversation variability for speaker diarization","author":"shum","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref17","article-title":"Unsupervised speaker adaptation based on the cosine similarity for text-independent speaker verification","author":"shum","year":"2010","journal-title":"Proc IEEE Odyssey"},{"key":"ref18","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":"ref19","article-title":"A spectral clustering approach to speaker diarization","author":"ning","year":"2006","journal-title":"Proc ICSLP"},{"key":"ref28","article-title":"Feature warping for robust speaker verification","author":"pelecanos","year":"2001","journal-title":"Proc A Speaker Odyssey"},{"key":"ref4","article-title":"The MIT Lincoln Laboratory RT-04F diarization systems: Applications to broadcast audio and telephone conversations","author":"reynolds","year":"2004","journal-title":"Proc NIST Rich Transcript Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894527"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref6","article-title":"Robust speaker diarization for meetings: ICSI RT06's evaluation system","author":"anguera","year":"2006","journal-title":"Proc ICSLP"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"ref5","author":"valente","year":"2005","journal-title":"Variational Bayesian methods for audio indexing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.002"},{"key":"ref7","article-title":"The IIR-NTU speaker diarization systems for rt 2009","author":"nguyen","year":"2009","journal-title":"Proc RT'09 NIST Rich Transcript Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.05.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495088"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","author":"shum","year":"2011","journal-title":"Unsupervised methods for speaker diarization"},{"key":"ref22","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2011-386","article-title":"Cross likelihood ratio based speaker clustering using eigenvoice models","author":"wang","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947362"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947363"},{"key":"ref24","article-title":"A global optimization framework for speaker diarization","author":"rouvier","year":"2012","journal-title":"Proc IEEE Odyssey"},{"key":"ref41","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IDAACS.2011.6072771"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.840940"},{"key":"ref25","article-title":"Mean shift algorithm for exponential families with applications to speaker clustering","author":"stafylakis","year":"2012","journal-title":"Proc IEEE Odyssey"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376\/6565391\/06518171.pdf?arnumber=6518171","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:22:38Z","timestamp":1715386958000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6518171\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,10]]},"references-count":42,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2013.2264673","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,10]]}}}