{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:49:19Z","timestamp":1752230959332,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":12,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642338847"},{"type":"electronic","value":"9783642338854"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-33885-4_39","type":"book-chapter","created":{"date-parts":[[2012,9,26]],"date-time":"2012-09-26T08:08:54Z","timestamp":1348646934000},"page":"385-394","source":"Crossref","is-referenced-by-count":10,"title":["Fusion of Speech, Faces and Text for Person Identification in TV Broadcast"],"prefix":"10.1007","author":[{"given":"Herv\u00e9","family":"Bredin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johann","family":"Poignant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Makarand","family":"Tapaswi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillaume","family":"Fortier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viet Bac","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thibault","family":"Napoleon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claude","family":"Barras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophie","family":"Rosset","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Besacier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakob","family":"Verbeek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georges","family":"Qu\u00e9not","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fr\u00e9d\u00e9ric","family":"Jurie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hazim Kemal","family":"Ekenel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4","key":"39_CR1","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1145\/954339.954342","volume":"35","author":"W. Zhao","year":"2003","unstructured":"Zhao, W., Chellappa, R., Phillips, P.J., Rosenfeld, A.: Face Recognition: a Literature Survey. ACM Comput. Surv.\u00a035(4), 399\u2013458 (2003)","journal-title":"ACM Comput. Surv."},{"key":"39_CR2","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1155\/S1110865704310024","volume":"2004","author":"F. Bimbot","year":"2004","unstructured":"Bimbot, F., Bonastre, J.F., Fredouille, C., Gravier, G., Magrin-Chagnolleau, I., Meignier, S., Merlin, T., Ortega-Garc\u00eda, J., Petrovska-Delacr\u00e9taz, D., Reynolds, D.A.: A Tutorial on Text-Independent Speaker Verification. EURASIP J. Appl. Signal Process.\u00a02004, 430\u2013451 (2004)","journal-title":"EURASIP J. Appl. Signal Process."},{"issue":"5","key":"39_CR3","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/TASL.2006.878261","volume":"14","author":"C. Barras","year":"2006","unstructured":"Barras, C., Zhu, X., Meignier, S., Gauvain, J.L.: Multi-Stage Speaker Diarization of Broadcast News. IEEE Transactions on Audio, Speech and Language Processing\u00a014(5), 1505\u20131512 (2006)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"39_CR4","unstructured":"Le, V.B., Barras, C., Ferr\u00e0s, M.: On the use of GSV-SVM for Speaker Diarization and Tracking. In: Proc. Odyssey 2010 - The Speaker and Language Recognition Workshop, Brno, Czech Republic, pp. 146\u2013150 (June 2010)"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Baeuml, M., Bernardin, K., Fischer, M., Ekenel, H., Stiefelhagen, R.: Multi-Pose Face Recognition for Person Retrieval in Camera Networks. In: Advanced Video and Signal-based Surveillance (2010)","DOI":"10.1109\/AVSS.2010.42"},{"key":"39_CR6","unstructured":"Ekenel, H., Stiefelhagen, R.: Analysis of Local Appearance Based Face Recognition: Effects of Feature Selection and Feature Normalization. In: CVPR Biometrics Workshop (2006)"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Everingham, M., Sivic, J., Zisserman, A.: \u201cHello! My name is... Buffy\u201d \u2013 Automatic Naming of Characters in TV video. In: British Machine Vision Conference (2006)","DOI":"10.5244\/C.20.92"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of Oriented Gradients for Human Detection. In: International Conference on Computer Vision & Pattern Recognition, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"issue":"1","key":"39_CR9","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/s11263-011-0447-x","volume":"96","author":"M. Guillaumin","year":"2012","unstructured":"Guillaumin, M., Mensink, T., Verbeek, J., Schmid, C.: Face Recognition from Caption-based Supervision. International Journal of Computer Vision\u00a096(1), 64\u201382 (2012)","journal-title":"International Journal of Computer Vision"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Poignant, J., Besacier, L., Qu\u00e9not, G., Thollard, F.: From Text Detection in Videos to Person Identification. In: IEEE ICME, Melbourne, Australia (2012)","DOI":"10.1109\/ICME.2012.119"},{"issue":"1-2","key":"39_CR11","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/S0167-6393(01)00061-9","volume":"37","author":"J. Gauvain","year":"2002","unstructured":"Gauvain, J., Lamel, L., Adda, G.: The LIMSI Broadcast News Transcription System. Speech Communication\u00a037(1-2), 89\u2013109 (2002)","journal-title":"Speech Communication"},{"key":"39_CR12","unstructured":"Dinarelli, M., Rosset, S.: Models Cascade for Tree-Structured Named Entity Detection. In: Proceedings of International Joint Conference of Natural Language Processing (IJCNLP), Chiang Mai, Thailand (November 2011)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2012. Workshops and Demonstrations"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-33885-4_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T14:16:01Z","timestamp":1744208161000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-33885-4_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642338847","9783642338854"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-33885-4_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}