{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T17:15:40Z","timestamp":1764350140269},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2012,2,1]],"date-time":"2012-02-01T00:00:00Z","timestamp":1328054400000},"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":[[2012,2]]},"DOI":"10.1109\/tasl.2011.2159710","type":"journal-article","created":{"date-parts":[[2012,1,31]],"date-time":"2012-01-31T18:28:23Z","timestamp":1328034503000},"page":"382-392","source":"Crossref","is-referenced-by-count":28,"title":["A Comparative Study of Bottom-Up and Top-Down Approaches to Speaker Diarization"],"prefix":"10.1109","volume":"20","author":[{"given":"Nicholas","family":"Evans","sequence":"first","affiliation":[]},{"given":"Simon","family":"Bozonnet","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Corinne","family":"Fredouille","sequence":"additional","affiliation":[]},{"given":"Rapha\u00ebl","family":"Troncy","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566478"},{"key":"ref38","first-page":"112","article-title":"Speaker turn detection based on between-channels differences","author":"ellis","year":"2004","journal-title":"NIST meeting recognition workshop at Proc ICASSP"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2007.905088"},{"key":"ref32","first-page":"347","article-title":"Two-way cluster voting to improve speaker diarisation performance","author":"tranter","year":"1997","journal-title":"Proc IEEE ASRU Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518621"},{"key":"ref30","first-page":"175","article-title":"E-HMM approach for learning and adapting sound models for speaker indexing","author":"meignier","year":"2001","journal-title":"Proc Odyssey Speaker Lang Recognition Workshop"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref36","article-title":"BeamformIt (the fast and robust acoustic beamformer)","author":"anguera","year":"0"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"2642","DOI":"10.21437\/Interspeech.2010-701","article-title":"System output combination for improved speaker diarization","author":"bozonnet","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"924","DOI":"10.21437\/Interspeech.2009-277","article-title":"The majority wins: A method for combining speaker diarization systems","author":"huijbregts","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-271","article-title":"Speaker diarization for meeting room audio","author":"sun","year":"2009","journal-title":"Proc Interspeech'09"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660196"},{"key":"ref11","article-title":"Robust speaker diarization for meetings: ICSI RT06s evaluation system","author":"anguera","year":"2006","journal-title":"Proc ICSLP"},{"key":"ref12","first-page":"127","article-title":"Speaker, environment and channel change detection and clustering via the Bayesian information criterion","author":"chen","year":"1998","journal-title":"Proc Broadcast News Transcription and Understanding Workshop"},{"key":"ref13","first-page":"509","article-title":"The ICSI RT07s speaker diarization system","author":"wooters","year":"2008","journal-title":"Proc Multimodal Technol for Perception of Humans Int Eval Workshops CLEAR 2007 and RT 2007 May 2007 Revised Sel Papers"},{"key":"ref14","first-page":"484","article-title":"Speaker diarization using direction of arrival estimate and acoustic feature information: The I2R-NTU submission for the NIST RT 2007 evaluation","author":"koh","year":"2008","journal-title":"Proc Multimodal Technol for Perception of Humans Int Eval Workshops CLEAR 2007 and RT 2007 May 8-11 2007 Revised Sel Papers"},{"key":"ref15","first-page":"475","article-title":"Progress in the AMIDA speaker diarization system for meeting data","author":"van leeuwen","year":"2008","journal-title":"Proc Multimodal Technol for Perception of Humans Int Eval Workshops CLEAR 2007 and RT 2007 May 8-11 2007 Revised Sel Papers"},{"key":"ref16","first-page":"543","article-title":"Speaker diarization for conference room: The UPC RT07s evaluation system","author":"luque","year":"2008","journal-title":"Proc Multimodal Technol for Perception of Humans Int Eval Workshops CLEAR 2007 and RT 2007 May 8-11 2007 Revised Sel Papers"},{"key":"ref17","first-page":"533","article-title":"Multi-stage speaker diarization for conference and lecture meetings","author":"zhu","year":"2008","journal-title":"Proc Multimodal Technol for Perception of Humans Int Eval Workshops CLEAR 2007 and RT 2007 May 8-11 2007 Revised Sel Papers"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-186","article-title":"Improvement speaker clustering using global similarity features","author":"biatov","year":"2006","journal-title":"Proc Interspeech 2006ICSLP"},{"key":"ref19","article-title":"Speaker diarization using bottom-up clustering based on a parameter-derived distance between adapted GMMs","author":"ben","year":"2004","journal-title":"Proc ICSLP"},{"key":"ref28","article-title":"The IIR-NTU speaker diarization systems for RT 2009","author":"nguyen","year":"2009","journal-title":"NIST Rich Transcription Workshop RT04"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/978-3-540-68585-2_47","volume":"4625 2008","author":"wooters","year":"2008","journal-title":"Lecture Notes in Computer ScienceMultimodal Technologies for Perception of Humans"},{"key":"ref27","article-title":"The AMI meeting corpus","author":"mccowan","year":"2005","journal-title":"Proc Meas Behav"},{"key":"ref3","year":"2009","journal-title":"The NIST Rich Transcript 2009 (RT'09) Eval"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495088"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2008-7","article-title":"T-test distance and clustering criterion for speaker diarization","author":"nguyen","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495077"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660198"},{"key":"ref7","first-page":"2246","article-title":"An integrated top-down\/bottom-up approach to speaker diarization","author":"bozonnet","year":"2010","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref9","article-title":"Frame purification for cluster comparison in speaker diarization","author":"anguera","year":"2006","journal-title":"Proc 2nd Int Workshop MultiModal User Authentification (MMUA)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2040796"},{"key":"ref22","first-page":"520","article-title":"The LIA RT'07 speaker diarization system","author":"fredouille","year":"2008","journal-title":"Proc Multimodal Technol for Perception of Humans Int Eval Workshops CLEAR 2007 and RT 2007 May 8-11 2007 Revised Sel Papers"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2002085"},{"key":"ref42","first-page":"97","article-title":"Automatic segmentation, classification and clustering of broadcast news audio","author":"siegler","year":"1997","journal-title":"Proc DARPA Speech Recognition Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518619"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015089"},{"key":"ref26","first-page":"21","article-title":"Qualcomm-ICSI-OGI features for ASR","author":"adami","year":"2002","journal-title":"Proc ICSLP"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415219"}],"container-title":["IEEE Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/10376\/6099652\/06135545.pdf?arnumber=6135545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:53:29Z","timestamp":1642006409000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6135545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2]]},"references-count":42,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tasl.2011.2159710","relation":{},"ISSN":["1558-7916","1558-7924"],"issn-type":[{"value":"1558-7916","type":"print"},{"value":"1558-7924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,2]]}}}