{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:16:06Z","timestamp":1775913366425,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771200"],"award-info":[{"award-number":["61771200"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3024667","type":"journal-article","created":{"date-parts":[[2020,9,21]],"date-time":"2020-09-21T21:18:22Z","timestamp":1600723102000},"page":"3377-3387","source":"Crossref","is-referenced-by-count":13,"title":["Speaker Clustering by Co-Optimizing Deep Representation Learning and Cluster Estimation"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4362-1125","authenticated-orcid":false,"given":"Yanxiong","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wucheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingle","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongjie","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianhua","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"146","article-title":"A global optimization framework for speaker diarization","author":"rouvier","year":"2012","journal-title":"Proc Odyssey"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495088"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2013.2285474"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495078"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68585-2_47"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2015698"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/iet-spr.2013.0340"},{"key":"ref60","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 DARPA Broad News Transcription Understanding Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-166"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2125954"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2009.03.001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2747097"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168166"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953183"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953094"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"411","DOI":"10.21437\/Interspeech.2019-1399","article-title":"Large-scale speaker diarization of radio broadcast archives","author":"y?lmaz","year":"2019","journal-title":"Proc INTERSPEECH"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2015.46"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45323-7_30"},{"key":"ref58","first-page":"373","article-title":"The rich transcription 2007 meeting recognition evaluation","volume":"4625","author":"fiscus","year":"2007","journal-title":"LNCS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2947199"},{"key":"ref56","first-page":"965","article-title":"Mobile phone clustering from speech recordings using deep embedding and spectral clustering","volume":"13","author":"li","year":"2018","journal-title":"IEEE TIFS"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.88"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref53","first-page":"1","article-title":"AISHELL-2: Transforming mandarin ASR research into industrial scale","author":"du","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2233724"},{"key":"ref11","first-page":"1694","article-title":"Multimodal multi-channel on-line speaker diarization using sensor fusion through SVM","volume":"17","author":"minotto","year":"2015","journal-title":"IEEE TMM"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"187","DOI":"10.21437\/Odyssey.2014-29","article-title":"Recent improvements on ILP-based clustering for broadcast news speaker diarization","author":"dupuy","year":"2014","journal-title":"Proc Odyssey"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74549-5_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2016-41"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.840940"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.876308"},{"key":"ref16","first-page":"i-725?728","article-title":"Clustering speech utterances by speaker using eigenvoice-motivated vector space models","author":"tsai","year":"2005","journal-title":"Proc ICASSP"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2009.01.002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-684"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2777671"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2791806"},{"key":"ref5","first-page":"2417","article-title":"Mean-shift and sparse sampling-based SMC-PHD filtering for audio informed visual speaker tracking","volume":"18","author":"k?l?\u00e7","year":"2016","journal-title":"IEEE TMM"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.09.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461893"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683683"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.174"},{"key":"ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4471-5779-3","author":"yu","year":"2015","journal-title":"Automatic Speech Recognition?A Deep Learning Approach"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003959"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683525"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2872931"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2007.909595"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2008.05.001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894525"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09201020.pdf?arnumber=9201020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T07:59:41Z","timestamp":1723622381000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9201020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3024667","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}