{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:05:54Z","timestamp":1725516354190},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540685845"},{"type":"electronic","value":"9783540685852"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-68585-2_49","type":"book-chapter","created":{"date-parts":[[2008,8,12]],"date-time":"2008-08-12T16:07:43Z","timestamp":1218557263000},"page":"533-542","source":"Crossref","is-referenced-by-count":7,"title":["Multi-stage Speaker Diarization for Conference and Lecture Meetings"],"prefix":"10.1007","author":[{"given":"X.","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.","family":"Barras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L.","family":"Lamel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J-L.","family":"Gauvain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"49_CR1","unstructured":"NIST, Spring 2007 Rich Transcription (RT-07S) Meeting Recognition Evaluation Plan (February 2007), http:\/\/www.nist.gov\/speech\/tests\/rt\/rt2007\/spring\/docs\/rt07s-meeting-eval-plan-v2.pdf"},{"key":"49_CR2","doi-asserted-by":"crossref","unstructured":"Anguera, X., Wooters, C., Hernando, J.: Speaker Diarization for Multi-Party Meetings Using Acoustic Fusion. In: Automatic Speech Recognition and Understanding (ASRU 2005), San Juan, Puerto Rico. IEEE, Los Alamitos (2005)","DOI":"10.1109\/ASRU.2005.1566478"},{"key":"49_CR3","doi-asserted-by":"crossref","unstructured":"Zhu, X., Barras, C., Meignier, S., Gauvain, J.-L.: Combining Speaker Identification and BIC for Speaker Diarization. In: ISCA Interspeech 2005, Lisbon, September 2005, pp. 2441\u20132444 (2005)","DOI":"10.21437\/Interspeech.2005-651"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Barras, C., Zhu, X., Meignier, S., Gauvain, J.-L.: Multi-Stage Speaker Diarization of Broadcast News. The IEEE Transactions on Audio, Speech and Language Processing, September 2006 (to appear)","DOI":"10.1109\/TASL.2006.878261"},{"key":"49_CR5","series-title":"Lecture Notes in Computer Science","volume-title":"Machine Learning for Multimodal Interaction","author":"X. Zhu","year":"2006","unstructured":"Zhu, X., Barras, C., Lamel, L., Gauvain, J.L.: Speaker Diarization: from Broadcast News to Lectures. In: Renals, S., Bengio, S. (eds.) MLMI 2005. LNCS, vol.\u00a03869, Springer, Heidelberg (2006)"},{"key":"49_CR6","unstructured":"Siegler, M., Jain, U., Raj, B., Stern, R.: Automatic segmentation and clustering of broadcast news audio. In: The DARPA Speech Recognition Workshop, Chantilly, USA (February 1997)"},{"key":"49_CR7","unstructured":"Chen, S., Gopalakrishnan, P.: Speaker, environment and channel change detection and clustering via the Bayesian information criterion. In: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, USA (February 1998)"},{"key":"49_CR8","unstructured":"Cettolo, M.: Segmentation, classification and clustering of an Italian broadcast news corpus. In: Conf. on Content-Based Multimedia Information Access (RIAO 2000), April 2000, Paris (2000)"},{"key":"49_CR9","unstructured":"Barras, C., Zhu, X., Meignier, S., Gauvain, J.L.: Improving speaker diarization. In: The Proceedings of Fall 2004 Rich Transcription Workshop (RT 2004), November 2004, Palisades, NY, USA (2004)"},{"key":"49_CR10","unstructured":"Tranter, S.E., Reynolds, D.A.: Speaker diarization for broadcast news. In: Proc. ISCA Speaker Recognition Workshop Odyssey 2004, May 2004, Toledo, Spain (2004)"},{"volume-title":"Digital Signal Processing (DSP), a review journal - Special issue on NIST 1999 speaker recognition workshop","year":"2000","key":"49_CR11","unstructured":"Schroeder, J., Campbell, J. (eds.): Digital Signal Processing (DSP), a review journal - Special issue on NIST 1999 speaker recognition workshop. Academic Press, London (2000)"},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Barras, C., Gauvain, J.-L.: Feature and score normalization for speaker verification of cellular data. In: IEEE ICASSP 2003, Hong Kong (2003)","DOI":"10.1109\/ICASSP.2003.1202291"},{"key":"49_CR13","unstructured":"Pelecanos, J., Sridharan, S.: Feature warping for robust speaker verification. In: Proc. ISCA Speaker Recognition Workshop Odyssey 2001, June 2001, pp. 213\u2013218 (2001)"},{"issue":"2","key":"49_CR14","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"J.-L. Gauvain","year":"1994","unstructured":"Gauvain, J.-L., Lee, C.H.: Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing\u00a02(2), 291\u2013298 (1994)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"issue":"1-3","key":"49_CR15","first-page":"19","volume":"10","author":"D.A. Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted Gaussian mixture models. Digital Signal Processing (DSP), a review journal - Special issue on NIST 1999 speaker recognition workshop\u00a010(1-3), 19\u201341 (2000)","journal-title":"Digital Signal Processing (DSP), a review journal - Special issue on NIST 1999 speaker recognition workshop"},{"key":"49_CR16","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., Singer, E., Carlson, B.A., O\u2019Leary, G.C., McLaughlin, J.J., Zissman, M.A.: Blind clustering of speech utterances based on speaker and language characteristics. In: Proc. of International Conf. on Spoken Language Processing (ICSLP 1998) (1998)","DOI":"10.21437\/ICSLP.1998-255"},{"key":"49_CR17","doi-asserted-by":"crossref","unstructured":"Stolcke, A., Anguera, X., Boakye, K., Cetin, O., Grezl, F., Janin, A., Mandal, A., Peskin, B., Wooters, C., Zheng, J.: The ICSI-SRI Spring 2005 Speech-To-Text evaluation System. In: Rich Transcription 2005 Spring Meeting Recognition Evaluation, July 2005, Edinburgh, Great Britain (2005)","DOI":"10.1007\/11677482_39"},{"key":"49_CR18","unstructured":"NIST, Fall 2004 Rich Transcription (RT-04F) evaluation plan (August 2004), http:\/\/www.nist.gov\/speech\/tests\/rt\/rt2004\/fall\/docs\/rt04f-eval-plan-v14.pdf"},{"key":"49_CR19","unstructured":"NIST, Spring 2006 Rich Transcription (RT-06S) Meeting Recognition Evaluation Plan (February 2006), http:\/\/www.nist.gov\/speech\/tests\/rt\/rt2006\/spring\/docs\/rt06s-meeting-eval-plan-v2.pdf"},{"key":"49_CR20","unstructured":"Wooters, C., Huijbregts, M.: The ICSI RT07s Speaker Diarization System. In: Rich Transcription 2007 Meeting Recognition Workshop, Baltimore, USA (May 2007)"}],"container-title":["Lecture Notes in Computer Science","Multimodal Technologies for Perception of Humans"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-68585-2_49.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T14:43:02Z","timestamp":1684507382000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-68585-2_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540685845","9783540685852"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-68585-2_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}