{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:04:10Z","timestamp":1783361050986,"version":"3.54.6"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540685845","type":"print"},{"value":"9783540685852","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-68585-2_44","type":"book-chapter","created":{"date-parts":[[2008,8,12]],"date-time":"2008-08-12T16:07:43Z","timestamp":1218557263000},"page":"475-483","source":"Crossref","is-referenced-by-count":12,"title":["Progress in the AMIDA Speaker Diarization System for Meeting Data"],"prefix":"10.1007","author":[{"given":"David A.","family":"van Leeuwen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matej","family":"Kone\u010dn\u00fd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Adami, A., Burget, L., Hermansky, H.: Qualcomm-ICSI-OGI noise-robust front end (September 2002), http:\/\/www.icsi.berkeley.edu\/Speech\/papers\/qio\/","DOI":"10.21437\/ICSLP.2002-4"},{"issue":"8","key":"44_CR2","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1109\/LSP.2004.831666","volume":"11","author":"J. Ajmera","year":"2004","unstructured":"Ajmera, J., McCowan, I., Bourlard, H.: Robust speaker change detection. IEEE Signal Processing Lettres\u00a011(8), 649\u2013651 (2004)","journal-title":"IEEE Signal Processing Lettres"},{"key":"44_CR3","unstructured":"Anguera, X.: BeamformIt, the fast and robust acoustic beamformer (2006), http:\/\/www.icsi.berkeley.edu\/~xanguera\/BeamformIt\/"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Anguera, X., Wooters, C., Peskin, B., Aguil\u00f3, M.: Robust speaker segmentation for meetings: The ICSI-SRI spring 2005 diarization system. In: Proc. RT 2005 Meeting Recognition Evaluation Workshop, Edinburgh, July 2005, pp. 26\u201338 (2005)","DOI":"10.1007\/11677482_34"},{"key":"44_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1007\/11677482_34","volume-title":"Machine Learning for Multimodal Interaction","author":"X. Anguera","year":"2006","unstructured":"Anguera, X., Wooters, C., Peskin, B., Aguil\u00f3, M.: Robust speaker segmentation for meetings: The ICSI-SRI spring 2005 diarization system. In: Renals, S., Bengio, S. (eds.) MLMI 2005. LNCS, vol.\u00a03869, pp. 402\u2013414. Springer, Heidelberg (2006)"},{"issue":"5","key":"44_CR6","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.: Multistage 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":"44_CR7","unstructured":"Chen, S.S., Gopalakrishnan, P.S.: Clustering via the Baysian Information Criterion with applications in speech recognition. In: Proc. ICASSP (1998)"},{"key":"44_CR8","unstructured":"Chen, S.S., Gopalakrishnan, P.S.: Speaker, environment and channel change detection and clustering via the Bayesian Information Criterion. In: Proceedings of the Darpa Broadcast News Transcription and Understanding Workshop (1998)"},{"key":"44_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/11677482_32","volume-title":"Machine Learning for Multimodal Interaction","author":"J. Fiscus","year":"2006","unstructured":"Fiscus, J., Radde, N., Garofolo, J.S., Le, A., Ajot, J., Laprun, C.: The rich transcription 2005 spring meeting recognition evaluation. In: Renals, S., Bengio, S. (eds.) MLMI 2005. LNCS, vol.\u00a03869, pp. 369\u2013389. Springer, Heidelberg (2006)"},{"key":"44_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/11965152_32","volume-title":"Machine Learning for Multimodal Interaction","author":"C. Fredouille","year":"2006","unstructured":"Fredouille, C., Senay, G.: Technical improvements of the e-hmm based speaker diarization system for meeting records. In: Renals, S., Bengio, S., Fiscus, J.G. (eds.) MLMI 2006. LNCS, vol.\u00a04299, pp. 359\u2013370. Springer, Heidelberg (2006)"},{"key":"44_CR11","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 esitimation for multivariate gaussian mixture observations of markov chains. IEEE Trans. Speech Audio Processing\u00a02, 291\u2013298 (1994)","journal-title":"IEEE Trans. Speech Audio Processing"},{"issue":"4","key":"44_CR12","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H. Hermansky","year":"1994","unstructured":"Hermansky, H., Morgan, N.: Rasta processing of speech. IEEE Transactions on Speech and Audio Processing, special issue on Robust Speech Recognition\u00a02(4), 578\u2013589 (1994)","journal-title":"IEEE Transactions on Speech and Audio Processing, special issue on Robust Speech Recognition"},{"issue":"4","key":"44_CR13","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","volume":"87","author":"H. Hermansky","year":"1990","unstructured":"Hermansky, H.: Perceptual linear predictive (plp) analysis of speech. JASA\u00a087(4), 1738\u20131752 (1990)","journal-title":"JASA"},{"key":"44_CR14","unstructured":"Huijbregts, M., Wooters, C., Ordelman, R.: Filtering the unknown: Speech activity detection in heterogeneous video collections. In: Proc. Interspeech, Antwerpen (accepted for publication, 2007)"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., Singer, E., Carlson, B.A.: Blind clustering of speech utterances based on speaker and language characteristics. In: Proceedings of International Conference Spoken Language Processing (ICSLP 1998), November 1998, pp. 3193\u20133196 (1998)","DOI":"10.21437\/ICSLP.1998-255"},{"key":"44_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/11677482_37","volume-title":"Machine Learning for Multimodal Interaction","author":"D.A. Leeuwen van","year":"2006","unstructured":"van Leeuwen, D.A.: The TNO speaker diarization system for NIST rich transcription evaluation 2005 for meeting data. In: Renals, S., Bengio, S. (eds.) MLMI 2005. LNCS, vol.\u00a03869, pp. 400\u2013449. Springer, Heidelberg (2006)"},{"key":"44_CR17","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74200-5_19","volume-title":"Speaker Classification I","author":"D.A. Leeuwen van","year":"2007","unstructured":"van Leeuwen, D.A., Br\u00fcmmer, N.: An introduction to application-independent evaluation of speaker recognition systems. In: M\u00fcller, C. (ed.) Speaker Classification 2007. LNCS (LNAI), vol.\u00a04343. Springer, Heidelberg (2007)"},{"key":"44_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/11965152_33","volume-title":"Machine Learning for Multimodal Interaction","author":"D.A. Leeuwen van","year":"2006","unstructured":"van Leeuwen, D.A., Huijbregts, M.: The AMI speaker diarization system for NIST RT06s meeting data. In: Renals, S., Bengio, S., Fiscus, J.G. (eds.) MLMI 2006. LNCS, vol.\u00a04299, pp. 371\u2013384. Springer, Heidelberg (2006)"},{"key":"44_CR19","unstructured":"Wooters, C., Huijbregts, M.: The ICSI RT07s speaker diarization system. In: Machine Learning for Multimodal Interaction. LNCS. Springer, Heidelberg (2007)"},{"key":"44_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/11965152_35","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., Fiscus, J.G. (eds.) MLMI 2006. LNCS, vol.\u00a04299, pp. 396\u2013406. Springer, Heidelberg (2006)"}],"container-title":["Lecture Notes in Computer Science","Multimodal Technologies for Perception of Humans"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-68585-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T14:42:53Z","timestamp":1684507373000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-68585-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540685845","9783540685852"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-68585-2_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008]]}}}