{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T16:04:25Z","timestamp":1779984265795,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,10,19]],"date-time":"2009-10-19T00:00:00Z","timestamp":1255910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,10,19]]},"DOI":"10.1145\/1631272.1631300","type":"proceedings-article","created":{"date-parts":[[2009,10,20]],"date-time":"2009-10-20T08:43:40Z","timestamp":1256028220000},"page":"185-194","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Unfolding speaker clustering potential"],"prefix":"10.1145","author":[{"given":"Thilo","family":"Stadelmann","sequence":"first","affiliation":[{"name":"University of Marburg, Marburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernd","family":"Freisleben","sequence":"additional","affiliation":[{"name":"University of Marburg, Marburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2009,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.02.005"},{"key":"e_1_3_2_1_2_1","volume-title":"A Day in the Life of a Gaussian Mixture Model: Informing Music Pattern Recognition with Psychological Experiments. Journal of New Music Research, submitted","author":"Aucouturier J.-J.","year":"2009","unstructured":"J.-J. Aucouturier. A Day in the Life of a Gaussian Mixture Model: Informing Music Pattern Recognition with Psychological Experiments. Journal of New Music Research, submitted, 2009."},{"issue":"1","key":"e_1_3_2_1_3_1","article-title":"Improving Timbre Similarity: How high is the sky?","volume":"1","author":"Aucouturier J.-J.","year":"2004","unstructured":"J.-J. Aucouturier and F. Pachet. Improving Timbre Similarity: How high is the sky? Journal of Negative Results in Speech and Audio Sciences, 1(1), 2004.","journal-title":"Journal of Negative Results in Speech and Audio Sciences"},{"key":"e_1_3_2_1_4_1","volume-title":"Bar-Cohen. Biomimetics: Biologically Inspired Technologies","author":"Y.","year":"2006","unstructured":"Y. Bar-Cohen. Biomimetics: Biologically Inspired Technologies. CRC Press, Boca Raton, FL, USA, 2006."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675374"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/1296217"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/1162264"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.628714"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"e_1_3_2_1_10_1","first-page":"185","volume-title":"Juang. Prosody Modeling and Eigen-Prosody Analysis for Robust Speaker Recognition. In Proc. IEEE Int. Conf. Acoust. Speech&Signal Proc. ICASSP'05","author":"Chen Z.-H.","unstructured":"Z.-H. Chen, Y.-F. Liao, and Y.-T. Juang. Prosody Modeling and Eigen-Prosody Analysis for Robust Speaker Recognition. In Proc. IEEE Int. Conf. Acoust. Speech&Signal Proc. ICASSP'05, pages I-185-I-188, 2005."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.725317"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2004-343"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.851098"},{"key":"e_1_3_2_1_15_1","first-page":"461","volume-title":"Proceedings of ESANN'2005","author":"Desobry F.","year":"2005","unstructured":"F. Desobry, M. Davy, and W. J. Fitzgerald. A Class of Kernels for Sets of Vectors. In Proceedings of ESANN'2005, pages 461--466. MIT Press, 2005."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/MAES.2005.1432568"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.11.006"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-580"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the DARPA Speech Recognition Workshop, Report No. SAIC-86\/1546","author":"Fisher W. M.","year":"1986","unstructured":"W. M. Fisher, G. R. Doddington, and K. M. Goudie-Marshall. The DARPA Speech Recognition Research Database: Specification and Status. In Proceedings of the DARPA Speech Recognition Workshop, Report No. SAIC-86\/1546, February 1986, Palo-Alto, 1986."},{"key":"e_1_3_2_1_20_1","volume-title":"Proc. SPECOM 2005","author":"Furui S.","year":"2005","unstructured":"S. Furui. 50 Years of Progress in Speech and Speaker Recognition. In Proc. SPECOM 2005, Patras, Greece, pages 1--9, 2005."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1206403"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2002085"},{"key":"e_1_3_2_1_24_1","first-page":"108","volume-title":"Proc. of the DARPA Speech Recognition Workshop","author":"Jin H.","year":"1997","unstructured":"H. Jin, F. Kubala, and R. Schwartz. Automatic Speaker Clustering. In Proc. of the DARPA Speech Recognition Workshop, pages 108--111, 1997."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2007613"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/270146"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.925152"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2007.11.017"},{"key":"e_1_3_2_1_29_1","first-page":"332","article-title":"Unsupervised Speaker Segmentation and Tracking","volume":"10","author":"Lie Lu H.-J. Z.","year":"2005","unstructured":"H.-J. Z. Lie Lu. Unsupervised Speaker Segmentation and Tracking in Real-Time Audio Content Analysis. Multimedia Systems, 10:332--343, 2005.","journal-title":"Real-Time Audio Content Analysis. Multimedia Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.12.003"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.880087"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89991-4_10"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.04.010"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.002"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2002-110"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.10.004"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/541177"},{"key":"e_1_3_2_1_38_1","volume-title":"Psychology of Hearing","author":"Moore B. C. J.","year":"2004","unstructured":"B. C. J. Moore. Psychology of Hearing, Fifth Edition. Elsevier Academic Press, London, UK, 2004."},{"key":"e_1_3_2_1_39_1","unstructured":"A. Morris D. Wu and J. Koreman. GMM based Clustering and Speaker Separability in the TIMIT Speech Database. Technical Report Saar-IP-08-08-2004 Saarland University 2004."},{"key":"e_1_3_2_1_40_1","first-page":"227","article-title":"Exploring Billions of Audio Features. In Eurasip, editor","volume":"07","author":"Pachet F.","year":"2007","unstructured":"F. Pachet and P. Roy. Exploring Billions of Audio Features. In Eurasip, editor, Proceedings of CBMI 07, pages 227--235, 2007.","journal-title":"Proceedings of CBMI"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.06.002"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings in Odyssey 2004","author":"Przybocki M.","year":"2004","unstructured":"M. Przybocki and A. Martin. NIST Speaker Recognition Evaluation Chronicles. In Proceedings in Odyssey 2004, 2004."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202760"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415079"},{"key":"e_1_3_2_1_45_1","volume-title":"NIST Rich Transcription Workshop","author":"Reynolds D.","year":"2004","unstructured":"D. Reynolds and P. Torres-Carrasquillo. The MIT Lincoln Laboratory RT-04F Diarization Systems: Applications to Broadcast News and Telephone Conversations. In NIST Rich Transcription Workshop November 2004, 2004."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1416463"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00009-D"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1006\/dspr.1999.0361"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/89.365379"},{"key":"e_1_3_2_1_50_1","volume-title":"London and New York","author":"Rose P.","year":"2002","unstructured":"P. Rose. Forensic Speaker Identification. Taylor&Francis, London and New York, 2002."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.5555\/340534.340792"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89991-4_24"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICISIP.2004.1287643"},{"key":"e_1_3_2_1_54_1","volume-title":"USA","author":"Smith S. W.","year":"2003","unstructured":"S. W. Smith. Digital Signal Processing - A Practical Guide for Engineers and Scientists. Newnes, USA, 2003."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-346"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/1367948.1367950"},{"key":"e_1_3_2_1_57_1","first-page":"495","volume-title":"Speech Coding and Synthesis","author":"Talkin D.","year":"1995","unstructured":"D. Talkin. A Robust Algorithm for Pitch Tracking (RAPT). In W. B. Klejin and K. K. Paliwal, editors, Speech Coding and Synthesis, chapter 3, pages 495--518. Elsevier Science, Amsterdam, NL, 1995."},{"key":"e_1_3_2_1_58_1","volume-title":"Technische Universteit Delft","author":"Tax D. M. J.","year":"2001","unstructured":"D. M. J. Tax. One-Class Classification - Concept-Learning in the Absence of Counter-Examples. PhD thesis, Technische Universteit Delft, 2001."},{"key":"e_1_3_2_1_59_1","first-page":"1","volume-title":"Group Delay Features for Speaker Recognition. In 6th International Conference on Information, Communications&Signal Processing","author":"Thiruvaran T.","year":"2007","unstructured":"T. Thiruvaran, E. Ambikairajah, and J. Epps. Group Delay Features for Speaker Recognition. In 6th International Conference on Information, Communications&Signal Processing, pages 1--5, 2007."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.878256"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.894525"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.07.001"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.5555\/876875.878994"},{"key":"e_1_3_2_1_64_1","unstructured":"D. Wu. Discriminative Preprocessing of Speech: Towards Improving Biometric Authentication. PhD thesis Saarland University 2006."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.12.013"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89796-5_71"}],"event":{"name":"MM09: ACM Multimedia Conference","location":"Beijing China","acronym":"MM09","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 17th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1631272.1631300","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1631272.1631300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T15:24:09Z","timestamp":1779981849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1631272.1631300"}},"subtitle":["a biomimetic approach"],"short-title":[],"issued":{"date-parts":[[2009,10,19]]},"references-count":66,"alternative-id":["10.1145\/1631272.1631300","10.1145\/1631272"],"URL":"https:\/\/doi.org\/10.1145\/1631272.1631300","relation":{},"subject":[],"published":{"date-parts":[[2009,10,19]]},"assertion":[{"value":"2009-10-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}