{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:42:56Z","timestamp":1752230576200,"version":"3.40.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2014,4,17]],"date-time":"2014-04-17T00:00:00Z","timestamp":1397692800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2015,2]]},"DOI":"10.1007\/s11042-014-1940-3","type":"journal-article","created":{"date-parts":[[2014,4,16]],"date-time":"2014-04-16T08:28:17Z","timestamp":1397636897000},"page":"1377-1396","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Lexical speaker identification in TV shows"],"prefix":"10.1007","volume":"74","author":[{"given":"Anindya","family":"Roy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Herv\u00e9","family":"Bredin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William","family":"Hartmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viet Bac","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claude","family":"Barras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Luc","family":"Gauvain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,4,17]]},"reference":[{"issue":"2","key":"1940_CR1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.specom.2012.08.007","volume":"55","author":"MJ Alam","year":"2013","unstructured":"Alam MJ, Kinnunen T, Kenny P, Ouellet P, O\u2019Shaughnessy D (2013) Multitaper MFCC and PLP features for speaker verification using i-vectors. Speech Commun 55(2):237\u2013251","journal-title":"Speech Commun"},{"key":"1940_CR2","unstructured":"Baker B, Vogt R, Mason M, Sridharan S (2004) Improved phonetic and lexical speaker recognition through MAP adaptation. In: Proceedings of Odyssey"},{"issue":"5","key":"1940_CR3","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/TASL.2006.878261","volume":"14","author":"C Barras","year":"2006","unstructured":"Barras C, Zhu X, Meignier S, Gauvain JL (2006) Multi-stage speaker diarization of broadcast news. IEEE Trans Audio Speech Lang Process 14(5):1505\u20131512","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1940_CR4","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1016\/j.specom.2012.06.003","volume":"54","author":"D Baum","year":"2012","unstructured":"Baum D (2012) Recognising speakers from the topics they talk about. Speech Comm 54:1132\u20131142","journal-title":"Speech Comm"},{"key":"1940_CR5","first-page":"993","volume":"3","author":"D Blei","year":"2003","unstructured":"Blei D, Ng A, Jordan M (2003) Latent dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"1940_CR6","unstructured":"Campbell W, Campbell J, Reynolds D, Jones D, Leek T (2003) Phonetic speaker recognition with support vector machines. In: Proceedings of neural information processing systems conference, pp 1377\u20131384"},{"issue":"5","key":"1940_CR7","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1109\/LSP.2006.870086","volume":"13","author":"W Campbell","year":"2006","unstructured":"Campbell W, Sturim D, Reynolds D (2006) Support vector machines using GMM supervectors for speaker verification. IEEE Signal Proc Lett 13(5):308\u2013311","journal-title":"IEEE Signal Proc Lett"},{"key":"1940_CR8","doi-asserted-by":"crossref","unstructured":"Canseco L, Lamel L, Gauvain JL (2005) A comparative study using manual and automatic transcriptions for diarization. In: Proceedings of IEEE workshop on Automatic Speech Recognition and Understanding (ASRU)","DOI":"10.1109\/ASRU.2005.1566507"},{"key":"1940_CR9","doi-asserted-by":"crossref","unstructured":"Dehak N, Dehak R, Kenny P, Brummer N, Ouellet P, Dumouchel P (2009) Support vector machines versus fast scoring in the low-dimensional total variability space for speaker verification. In: Proceedings of interspeech, pp 1559\u20131562","DOI":"10.21437\/Interspeech.2009-385"},{"issue":"4","key":"1940_CR10","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak N, Kenny P, Dehak R, Dumouchel P, Ouellet P (2011) Front-end factor analysis For speaker verification. IEEE Trans Audio Speech Lang Process 19(4):788\u2013798","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"1940_CR11","unstructured":"Doddington G (2001) Some experiments on ideolectal differences among speakers. Tech. rep. http:\/\/www.nist.gov\/speech\/tests\/spk\/2001\/doc\/"},{"key":"1940_CR12","doi-asserted-by":"crossref","unstructured":"Doddington G (2001) Speaker recognition based on idiolectal differences between speakers. In: Proceedings of interspeech","DOI":"10.21437\/Eurospeech.2001-417"},{"key":"1940_CR13","unstructured":"Galibert O, Kahn J (2013) The first official REPERE evaluation. In: Proceedings of workshop on Speech, Language and Audio in Multimedia (SLAM)"},{"key":"1940_CR14","doi-asserted-by":"crossref","unstructured":"Gauvain JL, Lamel L, Adda G (1998) Partitioning and transcription of broadcast news data. In: Proceedings of International Conference on Spoken Language Processing (ICSLP), pp 5:1335\u20131338","DOI":"10.21437\/ICSLP.1998-618"},{"key":"1940_CR15","doi-asserted-by":"crossref","unstructured":"Gauvain JL, Lamel L, Barras C, Adda G, de Kercadio Y (2000) The LIMSI SDR system for TREC-9. In: Proceedings of TREC-9","DOI":"10.6028\/NIST.SP.500-249.limsi-tlp"},{"key":"1940_CR16","unstructured":"Giraudel A, Carre M, Mapelli V, Kahn J, Galibert O, Quintard L (2012) The REPERE corpus : a multimodal corpus for person recognition. In: Proceedings of Language Resources and Evaluation Conference (LREC)"},{"issue":"6","key":"1940_CR17","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/S0306-4573(00)00015-7","volume":"36","author":"KS Jones","year":"2000","unstructured":"Jones KS, Walker S, Robertson S (2000) A probabilistic model of information retrieval: development and comparative experiments. Inf Process Manag 36(6):779\u2013840","journal-title":"Inf Process Manag"},{"key":"1940_CR18","doi-asserted-by":"crossref","unstructured":"Kajarekar SS, Ferrer L, Shriberg E, Sonmez K, Stolcke A, Venkataraman A, Zheng J (2005) SRI\u2019s 2004 NIST speaker recognition evaluation system. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP.2005.1415078"},{"key":"1940_CR19","doi-asserted-by":"crossref","unstructured":"Khan A, Yegnanarayana B (2004) Latent semantic analysis for speaker recognition. In: Proceedings of International Conference on Spoken Language Processing (ICSLP)","DOI":"10.21437\/Interspeech.2004-543"},{"issue":"1","key":"1940_CR20","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T Kinnunen","year":"2010","unstructured":"Kinnunen T, Li H (2010) An overview of text-independent speaker recognition: from features to supervectors. Speech Comm 52(1):12\u201340","journal-title":"Speech Comm"},{"key":"1940_CR21","unstructured":"Lamel L, Courcinous S, Despres J, Gauvain JL, Josse Y, Kilgour K, Kraft F, Le VB, Nussbaum-Thom HNM, Oparin I, Schlippe T, Schluter R, Schultz T, da Silva TF, Stuker S, Sundermeyer M, Vieru B, Vu NT, Waibel A, Woehrling C (2011) Speech recognition for machine translation in quaero. In: Proceedings of IWSLT"},{"key":"1940_CR22","unstructured":"Le V, Barras C, Ferras M (2010) On the use of GSV-SVM for speaker diarization and tracking. In: Proceedings of Odyssey, pp 146\u2013150"},{"key":"1940_CR23","doi-asserted-by":"crossref","unstructured":"Manning C, Raghavan P, Schutze H (2008) Introduction to information retrieval. Cambridge University Press","DOI":"10.1017\/CBO9780511809071"},{"key":"1940_CR24","doi-asserted-by":"crossref","unstructured":"Mauclair J, Meignier S, Esteve Y (2006) Speaker diarization: about whom the speaker is talking?. In: Proceedings of Odyssey","DOI":"10.1109\/ODYSSEY.2006.248114"},{"key":"1940_CR25","unstructured":"McCallum A (2002) Mallet: a machine learning for language toolkit. Tech. rep. http:\/\/mallet.cs.umass.edu"},{"key":"1940_CR26","doi-asserted-by":"crossref","unstructured":"Plchot O, Matsoukas S, Matejka P, Dehak N, Ma J, Cumani S, Glembek O, Hermansky H, Mallidi S, Mesgarani N, Schwartz R, Soufifar M, Tan Z, Thomas S, Zhang B, Zhou X (2013) Developing a speaker identification system for the DARPA RATS project. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP.2013.6638972"},{"key":"1940_CR27","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1007\/978-3-540-74200-5_14","volume":"4343","author":"E Shriberg","year":"2007","unstructured":"Shriberg E (2007) Higher-level features in speaker recognition. Speaker Classification I. LNAI 4343: 241\u2013259","journal-title":"Speaker Classification I. LNAI"},{"key":"1940_CR28","doi-asserted-by":"crossref","unstructured":"Tran VA, Le V, Barras C, Lamel L (2011) Comparing multi-stage approaches for cross-show speaker diarization. In: Proceedings of interspeech, pp 1053\u20131056","DOI":"10.21437\/Interspeech.2011-392"},{"key":"1940_CR29","doi-asserted-by":"crossref","unstructured":"Tranter S (2006) Who really spoke when? Finding speaker turns and identities in broadcast news audio. In: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","DOI":"10.1109\/ICASSP.2006.1660195"},{"key":"1940_CR30","doi-asserted-by":"crossref","unstructured":"Tur G, Shriberg E, Stolcke A, Kajarekar S (2007) Duration and pronunciation conditioned lexical modeling for speaker verification. In: Proceedings of interspeech","DOI":"10.21437\/Interspeech.2007-172"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-1940-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-014-1940-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-014-1940-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T11:32:27Z","timestamp":1746185547000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-014-1940-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,4,17]]},"references-count":30,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,2]]}},"alternative-id":["1940"],"URL":"https:\/\/doi.org\/10.1007\/s11042-014-1940-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2014,4,17]]}}}