{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T06:05:55Z","timestamp":1725516355137},"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_50","type":"book-chapter","created":{"date-parts":[[2008,8,12]],"date-time":"2008-08-12T16:07:43Z","timestamp":1218557263000},"page":"543-553","source":"Crossref","is-referenced-by-count":6,"title":["Speaker Diarization for Conference Room: The UPC RT07s Evaluation System"],"prefix":"10.1007","author":[{"given":"Jordi","family":"Luque","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"Anguera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Temko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Hernando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"50_CR1","unstructured":"NIST: Rich transcription meeting recognition evaluation plan. RT-07s (2007)"},{"key":"50_CR2","doi-asserted-by":"crossref","unstructured":"Anguera, X., Wooters, C., Hernando, J.: Robust speaker diarization for meetings: Icsi rt06s evaluation system. In: ICSLP (2006)","DOI":"10.1007\/11965152_31"},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Gauvain, J., Lamel, L., Adda, G.: Partitioning and transcription of broadcast news data. In: ICSLP, pp. 1335\u20131338 (1998)","DOI":"10.21437\/ICSLP.1998-618"},{"key":"50_CR4","unstructured":"Chen, S., Gopalakrishnan, P.: Speaker, environment and channel change detection and clustering via the bayesian information criterion. In: DARPA BNTU Workshop (1998)"},{"key":"50_CR5","doi-asserted-by":"crossref","unstructured":"Gish, H., Siu, M., Rohlicek, R.: Segregation of speakers for speech recognition and speaker identification. In: ICASSP (1991)","DOI":"10.1109\/ICASSP.1991.150477"},{"key":"50_CR6","doi-asserted-by":"crossref","unstructured":"Adami, A., et al.: Qualcomm-icsi-cgi features for asr. In: ICSLP, pp. 21\u201324 (2002)","DOI":"10.21437\/ICSLP.2002-4"},{"key":"50_CR7","unstructured":"Anguera, X.: The acoustic robust beamforming toolkit (2005)"},{"key":"50_CR8","doi-asserted-by":"crossref","unstructured":"Temko, A., Macho, D., Nadeu, C.: Enhanced SVM Training for Robust Speech Activity Detection. In: Proc. ICCASP (2007)","DOI":"10.1109\/ICASSP.2007.367247"},{"key":"50_CR9","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1016\/S0167-6393(97)00030-7","volume":"22","author":"C. Nadeu","year":"1997","unstructured":"Nadeu, C., Paches-Leal, P., Juang, B.H.: Filtering the time sequence of spectral parameters for speech recognition. Speech Communication\u00a022, 315\u2013332 (1997)","journal-title":"Speech Communication"},{"issue":"5","key":"50_CR10","doi-asserted-by":"crossref","first-page":"1508","DOI":"10.1121\/1.392786","volume":"78","author":"J. Flanagan","year":"1985","unstructured":"Flanagan, J., Johnson, J., Kahn, R., Elko, G.: Computer-steered microphone arrays for sound transduction in large rooms. ASAJ\u00a078(5), 1508\u20131518 (1985)","journal-title":"ASAJ"},{"issue":"4","key":"50_CR11","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1109\/TASSP.1976.1162830","volume":"24","author":"C. Knapp","year":"1976","unstructured":"Knapp, C., Carter, G.: The generalized correlation method for estimation of time delay. IEEE Transactions on Acoustic, Speech and Signal Processing\u00a024(4), 320\u2013327 (1976)","journal-title":"IEEE Transactions on Acoustic, Speech and Signal Processing"},{"key":"50_CR12","volume-title":"Learning with Kernels","author":"B. Sch\u00f6lkopf","year":"2002","unstructured":"Sch\u00f6lkopf, B., Smola, A.: Learning with Kernels. MIT Press, Cambridge (2002)"},{"key":"50_CR13","doi-asserted-by":"crossref","unstructured":"Fung, G., Mangasarian, O.: Proximal Support Vector Machine Classifiers. In: Proc. KDDM, pp. 77\u201386 (2001)","DOI":"10.1145\/502512.502527"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Lebrun, G., Charrier, C., Cardot, H.: SVM Training Time Reduction using Vector Quantization. In: Proc. ICPR, pp. 160\u2013163 (2004)","DOI":"10.1109\/ICPR.2004.1334035"},{"key":"50_CR15","doi-asserted-by":"crossref","unstructured":"Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Transactions ASSP\u00a0(28), 357\u2013366 (1980)","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"50_CR16","unstructured":"Luque, J., Hernando, J.: Robust Speaker Identification for Meetings: UPC CLEAR-07 Meeting Room Evaluation System. In: The same book (2007)"},{"key":"50_CR17","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/S0167-6393(00)00048-0","volume":"34","author":"C. Nadeu","year":"2001","unstructured":"Nadeu, C., Macho, D., Hernando, J.: Time and Frequency Filtering of Filter-Bank Energies for Robust Speech Recognition. Speech Communication\u00a034, 93\u2013114 (2001)","journal-title":"Speech Communication"},{"key":"50_CR18","unstructured":"Macho, D., Nadeu, C.: On the interaction between time and frequency filterinf of speech parameters for robust speech recognition. In: ICSLP, 1137 (1999)"},{"key":"50_CR19","unstructured":"Anguera, X., Hernando, J., Anguita, J.: Xbic: nueva medida para segmentaci\u00f3n de locutor hacia el indexado autom\u00e1tico de la se\u00f1al de voz. JTH, 237\u2013242 (2004)"},{"key":"50_CR20","doi-asserted-by":"crossref","unstructured":"Nadeu, C., Hernando, J., Gorricho, M.: On the Decorrelation of filter-Bank Energies in Speech Recognition. In: EuroSpeech, vol.\u00a020, p. 417 (1995)","DOI":"10.21437\/Eurospeech.1995-220"}],"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_50.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T14:42:56Z","timestamp":1684507376000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-68585-2_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540685845","9783540685852"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-68585-2_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[]}}