{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:45:01Z","timestamp":1790685901753,"version":"4.1.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2015,1]]},"DOI":"10.1109\/taslp.2014.2367822","type":"journal-article","created":{"date-parts":[[2014,11,6]],"date-time":"2014-11-06T15:20:32Z","timestamp":1415287232000},"page":"57-68","source":"Crossref","is-referenced-by-count":14,"title":["Unsupervised Speaker Identification in TV Broadcast Based on Written Names"],"prefix":"10.1109","volume":"23","author":[{"given":"Johann","family":"Poignant","sequence":"first","affiliation":[{"name":"CNRS, LIG, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Besacier","sequence":"additional","affiliation":[{"name":"CNRS, LIG, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georges","family":"Que\u0301not","sequence":"additional","affiliation":[{"name":"LIG, Univ. Grenoble Alpes, Grenoble, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2006.870086"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref33","first-page":"121","article-title":"Speech recognition for machine translation in Quaero","author":"lamel","year":"2011","journal-title":"Proc Int Workshop Spoken Lang Translation"},{"key":"ref32","article-title":"Global optimization framework for speaker diarization","author":"rouvier","year":"2012","journal-title":"Proc Odyssey"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878261"},{"key":"ref30","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 Broadcast News Transcript Understand Workshop"},{"key":"ref37","first-page":"289","article-title":"Limsi participation in the QAst 2009track: Experimenting on answer scoring","author":"bernard","year":"2009","journal-title":"Proc CLEF"},{"key":"ref36","article-title":"Training and evaluation of POS taggers on the French multitag corpus","author":"allauzen","year":"2008","journal-title":"Proc LREC"},{"key":"ref35","first-page":"1269","article-title":"Models cascade for tree-structured named entity detection","author":"dinarelli","year":"2011","journal-title":"Proc Int Joint Conf Nat Lang Process"},{"key":"ref34","first-page":"1335","article-title":"Partitioning and transcription of broadcast news data","author":"gauvain","year":"1998","journal-title":"Proc ICSLP"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960644"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14055-6_19"},{"key":"ref40","first-page":"146","article-title":"On the use of GSV-SVM for speaker diarization and tracking","author":"le","year":"2010","journal-title":"Proc Odyssey"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6289062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/93.752960"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5254.796089"},{"key":"ref16","first-page":"10","article-title":"Naming every individual in news video monologues","author":"yang","year":"2004","journal-title":"Proc ACM Multimedia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s005300050140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.119"},{"key":"ref4","article-title":"Speaker identity indexing in audio-visual documents","author":"charhad","year":"2005","journal-title":"Proc CBMI"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2012.6269851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566507"},{"key":"ref27","article-title":"Unsupervised naming of speakers in broadcast TV: Using written names, pronounced names or both","author":"poignant","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1660195"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00061-9"},{"key":"ref29","article-title":"The REPERE corpus: A multi-modal corpus for person recognition","author":"giraudel","year":"2012","journal-title":"Proc LREC"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ODYSSEY.2006.248114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366899"},{"key":"ref2","article-title":"Speaker diarization from speech transcripts","author":"canseco-rodriguez","year":"2004","journal-title":"Proc INTERSPEECH"},{"key":"ref9","first-page":"2601","article-title":"Extracting true speaker identities from transcriptions","author":"est\ufffdve","year":"2007","journal-title":"Proc INTERSPEECH"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878261"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33885-4_39"},{"key":"ref22","first-page":"49","article-title":"Qcompere at repere 2013","author":"bredin","year":"2013","journal-title":"Proc of SLAML"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"2650","DOI":"10.21437\/Interspeech.2012-344","article-title":"Unsupervised speaker identification using overlaid texts in TV broadcast","author":"poignant","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref24","article-title":"Integer linear programming for speaker diarization and cross-modal identification in tv broadcast","author":"bredin","year":"2013","journal-title":"Proc INTERSPEECH"},{"key":"ref23","article-title":"Towards a better integration of written names for unsupervised speakers identification in videos","author":"poignant","year":"2013","journal-title":"Proc of SLAML"},{"key":"ref26","article-title":"Nommage non-supervis\ufffd des personnes dans les \ufffdmissions de t\ufffdl\ufffdvision: Une revue du potentiel de chaque modalit\ufffd","author":"poignant","year":"2013","journal-title":"CORIA"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/7010069\/06949118.pdf?arnumber=6949118","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T21:22:04Z","timestamp":1771449724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6949118\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1]]},"references-count":40,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2014.2367822","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1]]}}}