{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,22]],"date-time":"2024-06-22T21:56:09Z","timestamp":1719093369498},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,7,31]],"date-time":"2012-07-31T00:00:00Z","timestamp":1343692800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1186\/1687-4722-2012-19","type":"journal-article","created":{"date-parts":[[2012,7,31]],"date-time":"2012-07-31T16:14:04Z","timestamp":1343751244000},"source":"Crossref","is-referenced-by-count":15,"title":["Speaker diarization of broadcast news in Albayzin 2010 evaluation campaign"],"prefix":"10.1186","volume":"2012","author":[{"given":"Martin","family":"Zelen\u00e1k","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrik","family":"Schulz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javier","family":"Hernando","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,7,31]]},"reference":[{"key":"56_CR1","first-page":"127","volume-title":"Proc. DARPA Broadcast News Transcription and Understanding Workshop","author":"S Chen","year":"1998","unstructured":"Chen S, Gopalakrishnan P: Speaker, environment and channel change detection and clustering via the Bayesian information criterion. Proc. DARPA Broadcast News Transcription and Understanding Workshop (1998), pp. 127\u2013132"},{"key":"56_CR2","volume-title":"Proc. 5th International Conference on Spoken Language Processing (ICSLP\u201998)","author":"J Gauvain","year":"1998","unstructured":"Gauvain J, Lamel LF, Adda G: Partitioning and transcription of broadcast news data. Proc. 5th International Conference on Spoken Language Processing (ICSLP\u201998) (Sydney, Australia, 1998), paper 0084"},{"key":"56_CR3","first-page":"97","volume-title":"Proc. DARPA Speech Recognition, Workshop","author":"MA Siegler","year":"1997","unstructured":"Siegler MA, Jain U, Raj B, Stern RM: Automatic segmentation, classification and clustering of broadcast news audio. Proc. DARPA Speech Recognition, Workshop (Chantilly, VA, USA, 1997), pp. 97\u201399"},{"key":"56_CR4","first-page":"411","volume-title":"Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU\u201903)","author":"J Ajmera","year":"2003","unstructured":"Ajmera J, Wooters C: A robust speaker clustering algorithm. Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU\u201903) (St. Thomas, VI, USA, 2003), pp. 411\u2013416","edition":"St. Thomas, VI,"},{"key":"56_CR5","first-page":"175","volume-title":"Proc. 2001: A Speaker Odyssey - The Speaker Recognition Workshop (Odyssey-2001)","author":"S Meignier","year":"2001","unstructured":"Meignier S, Bonastre J, Igounet S: E-HMM approach for learning and adapting sound models for speaker indexing. Proc. 2001: A Speaker Odyssey - The Speaker Recognition Workshop (Odyssey-2001) (Crete, Greece, 2001), pp. 175\u2013180"},{"key":"56_CR6","first-page":"I\/161","volume-title":"Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201994)","author":"L Wilcox","year":"1994","unstructured":"Wilcox L, Chen F, Kimber D, Balasubramanian V: Segmentation of speech using speaker identification. Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP\u201994), vol. 1 (Adelaide, Australia, 1994), pp. I\/161\u2013I\/164"},{"key":"56_CR7","first-page":"470","volume-title":"Proc. ICSLP\u201900","author":"DA Reynolds","year":"2000","unstructured":"Reynolds DA, Dunn RB, McLaughlin JL: The Lincoln Speaker Recognition System: NIST Eval2000. Proc. ICSLP\u201900, vol. 2 (Beijing, China, 2000), pp. 470\u2013473"},{"key":"56_CR8","first-page":"355","volume-title":"Proc. Odyssey-2004 The Speaker and Language Recognition Workshop","author":"D Moraru","year":"2004","unstructured":"Moraru D, Besacier L, Castelli E: Using a priori information for speaker diarization. Proc. Odyssey-2004 The Speaker and Language Recognition Workshop (Toledo, Spain 2004), pp. 355\u2013362"},{"issue":"2-3","key":"56_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.csl.2005.08.002","volume":"20","author":"S Meignier","year":"2006","unstructured":"Meignier S, Moraru D, Fredouille C, Bonastre J, Besacier L: Step-by-step and integrated approaches in broadcast news speaker diarization. Comput. Speech Lang 2006, 20(2-3):303-330. 10.1016\/j.csl.2005.08.002","journal-title":"Comput. Speech Lang"},{"key":"56_CR10","unstructured":"FALA: FALA 2010 Proceedings (2010) . Accessed 30 May 2011 http:\/\/fala2010.uvigo.es\/images\/proceedings\/"},{"key":"56_CR11","unstructured":"NIST: The NIST rich transcription evaluation project website (2009) . Accessed 30 May 2011 http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/rt\/"},{"key":"56_CR12","first-page":"4133","volume-title":"Proc. ICASSP\u201908","author":"F Castaldo","year":"2008","unstructured":"Castaldo F, Colibro D, Dalmasso E, Laface P, Vair C: Stream-based speaker segmentation using speaker factors and eigenvoices. Proc. ICASSP\u201908 (Las Vegas, NV, USA, 2008), pp. 4133\u20134136"},{"key":"56_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1007\/978-3-642-21257-4_76","volume-title":"Pattern Recognition and Image Analysis","author":"M Diez","year":"2011","unstructured":"Diez M, Penagarikano M, Varona A, Rodriguez-Fuentes L, Bordel G: On the use of dot scoring for speaker diarization. Pattern Recognition and Image Analysis, vol. 6669 of Lecture Notes in Computer Science (Springer, Berlin, 2011), pp. 612\u2013619","edition":"6669"},{"key":"56_CR14","volume-title":"Proc. ISMIR\u201902","author":"J Haitsma","year":"2002","unstructured":"Haitsma J, Kalker T: A highly robust audio fingerprinting system. Proc. ISMIR\u201902 2002."},{"key":"56_CR15","first-page":"1149","volume-title":"Proc. Interspeech\u201905","author":"S Galliano","year":"2005","unstructured":"Galliano S, Geoffrois E, Mostefa D, Choukri K, Bonastre JF, Gravier G: The ESTER phase II evaluation campaign for the rich transcription of French broadcast news. Proc. Interspeech\u201905 (Lisbon, Portugal, 2005), pp. 1149\u20131152"},{"key":"56_CR16","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780199258147.001.0001","volume-title":"The Phonology of Catalan","author":"MW Wheeler","year":"2005","unstructured":"Wheeler MW: The Phonology of Catalan. (Oxford University Press, Oxford, 2005)","edition":"Oxford Universi"},{"key":"56_CR17","first-page":"17","volume-title":"Proc. Workshop on Speech and Language Technologies for Iberian Languages","author":"M Aguil\u00f3","year":"2009","unstructured":"Aguil\u00f3 M, Butko T, Temko A, Nadeu C: A hierarchical architecture for audio segmentation in a broadcast news task. Proc. Workshop on Speech and Language Technologies for Iberian Languages (Porto Salvo, Portugal, 2009), pp. 17\u201320"},{"key":"56_CR18","first-page":"301","volume-title":"Proc. FALA 2010","author":"M Zelen\u00e1k","year":"2010","unstructured":"Zelen\u00e1k M, Schulz H, Hernando J: Albayzin 2010 evaluation campaign: speaker diarization. Proc. FALA 2010 (Vigo, Spain, 2010), pp. 301\u2013304"},{"key":"56_CR19","volume-title":"Proc. FALA 2010","author":"T Butko","year":"2010","unstructured":"Butko T, Nadeu C, Schulz H: Albayzin-2010 audio segmentation evaluation: evaluation setup and results. Proc. FALA 2010 2010."},{"issue":"2","key":"56_CR20","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner L: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 1989, 77(2):257-286. 10.1109\/5.18626","journal-title":"Proc. IEEE"},{"key":"56_CR21","first-page":"679","volume-title":"Proc. Eurospeech\u201999","author":"A Tritschler","year":"1999","unstructured":"Tritschler A, Gopinath RA: Improved speaker segmentation and segments clustering using the Bayesian information criterion. Proc. Eurospeech\u201999 (Budapest, Hungary 1999), pp. 679\u2013682"},{"key":"56_CR22","first-page":"481","volume-title":"Proc. Conference on Telecommunications (ConfTele2009)","author":"C Neves","year":"2009","unstructured":"Neves C, Veiga A, S\u00e1 L, Perdig\u00e3o F: Fingerprinting system for broadcast streams. Proc. Conference on Telecommunications (ConfTele2009) (2009), pp. 481\u2013484"},{"issue":"6","key":"56_CR23","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1109\/89.876308","volume":"8","author":"R Kuhn","year":"2000","unstructured":"Kuhn R, Junqua JC, Nguyen P, Niedzielski N: Rapid speaker adaptation in eigenvoice space. IEEE Trans. Speech Audio Process 2000, 8(6):695-707. 10.1109\/89.876308","journal-title":"IEEE Trans. Speech Audio Process"},{"key":"56_CR24","volume-title":"Pattern Classification","author":"RO Duda","year":"2000","unstructured":"Duda RO, Hart PE, Stork DG: Pattern Classification,. (Wiley-Interscience, New York, 2000)"},{"key":"56_CR25","first-page":"2310","volume-title":"Proc. Interspeech\u201910","author":"C Vaquero","year":"2010","unstructured":"Vaquero C, Ortega A, Villalba J, Miguel A, Lleida E: Confidence measures for speaker segmentation and their relation to speaker verification. Proc. Interspeech\u201910 (Makuhari, Japan, 2010), pp. 2310\u20132313"},{"key":"56_CR26","first-page":"V","volume-title":"Proc. ICASSP\u201906","author":"A Hatch","year":"2006","unstructured":"Hatch A, Stolcke A: Generalized linear kernels for one-versus-all classification: application to speaker recognition. Proc. ICASSP\u201906 vol. 5 (Toulouse, France, 2006), p. V","edition":"5"},{"key":"56_CR27","first-page":"237","volume-title":"III Jornadas en Tecnolog\u00eda del Habla","author":"X Anguera","year":"2004","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. III Jornadas en Tecnolog\u00eda del Habla (Valencia, Spain, 2004), pp. 237\u2013242"},{"issue":"1-3","key":"56_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1006\/dspr.1999.0360","volume":"10","author":"R Auckenthaler","year":"2000","unstructured":"Auckenthaler R, Carey M, Lloyd-Thomas H: Score normalization for text-independent speaker verification systems. Digital Signal Process 2000, 10(1-3):42-54. 10.1006\/dspr.1999.0360","journal-title":"Digital Signal Process"},{"issue":"4","key":"56_CR29","doi-asserted-by":"publisher","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 Trans. Speech Audio Process 1994, 2(4):578-589. 10.1109\/89.326616","journal-title":"IEEE Trans. Speech Audio Process"},{"key":"56_CR30","first-page":"213","volume-title":"Proc. 2001: A Speaker Odyssey\u2014The Speaker Recognition Workshop (Odyssey-2001)","author":"J Pelecanos","year":"2001","unstructured":"Pelecanos J, Sridharan S: Feature warping for robust speaker verification. Proc. 2001: A Speaker Odyssey\u2014The Speaker Recognition Workshop (Odyssey-2001) (Crete, Greece, 2001), pp. 213\u2013218"},{"key":"56_CR31","first-page":"788","volume-title":"Front-end factor analysis for speaker verification","author":"N Dehak","year":"2011","unstructured":"Dehak N, Kenny P, Dehak R, Dumouchel P, Ouellet P: Front-end factor analysis for speaker verification. 2011, 788-798."},{"key":"56_CR32","first-page":"71","volume-title":"Proc. Odyssey 2010: The Speaker and Language Recognition Workshop","author":"N Dehak","year":"2010","unstructured":"Dehak N, Dehak R, Glass J, Reynolds D, Kenny P: Cosine similarity scoring without score normalization techniques. Proc. Odyssey 2010: The Speaker and Language Recognition Workshop (Brno, Czech Republic, 2010), pp. 71\u201375"},{"key":"56_CR33","first-page":"I","volume-title":"Proc. ICASSP\u201906","author":"N Mirghafori","year":"2006","unstructured":"Mirghafori N, Wooters C: Nuts and flakes: a study of data characteristics in speaker diarization. Proc. ICASSP\u201906 vol. 1 (Toulouse, France, 2006), p. I","edition":"1"},{"key":"56_CR34","unstructured":"Fiscus J, Le A, Sanders G: MDE Tasks and Results(2004). . Accessed 30 May 2011 http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/rt\/2004-fall\/rt04f-mde-nist.pdf"}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2012-19\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2012-19.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2012-19.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T23:53:02Z","timestamp":1714261982000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2012-19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,7,31]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2012,12]]}},"alternative-id":["56"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2012-19","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,7,31]]},"article-number":"19"}}