{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T13:17:42Z","timestamp":1740143862283,"version":"3.37.3"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,7,9]],"date-time":"2019-07-09T00:00:00Z","timestamp":1562630400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,7,9]],"date-time":"2019-07-09T00:00:00Z","timestamp":1562630400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100010909","name":"Young Scientists Fund","doi-asserted-by":"publisher","award":["61403224"],"award-info":[{"award-number":["61403224"]}],"id":[{"id":"10.13039\/501100010909","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s13636-019-0154-z","type":"journal-article","created":{"date-parts":[[2019,7,9]],"date-time":"2019-07-09T14:14:22Z","timestamp":1562681662000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Latent class model with application to speaker diarization"],"prefix":"10.1186","volume":"2019","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4076-7479","authenticated-orcid":false,"given":"Liang","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael T.","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,9]]},"reference":[{"issue":"2","key":"154_CR1","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","volume":"20","author":"X. A. Miro","year":"2012","unstructured":"X. A. Miro, S. Bozonnet, N. Evans, C. Fredouille, G. Friedland, O. Vinyals, Speaker diarization: a review of recent research. IEEE Trans. Audio Speech Lang. Process.20(2), 356\u2013370 (2012). https:\/\/doi.org\/10.1109\/TASL.2011.2125954 .","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"6","key":"154_CR2","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1109\/JSTSP.2010.2081790","volume":"4","author":"P. Kenny","year":"2010","unstructured":"P. Kenny, D. Reynolds, F. Castaldo, Diarization of telephone conversations using factor analysis. IEEE J. Sel. Top. Signal Proc.4(6), 1059\u20131070 (2010). https:\/\/doi.org\/10.1109\/JSTSP.2010.2081790 .","journal-title":"IEEE J. Sel. Top. Signal Proc."},{"unstructured":"P. Kenny, Bayesian analysis of speaker diarization with eigenvoice priors. Technical report, CRIM (2008).","key":"154_CR3"},{"key":"154_CR4","doi-asserted-by":"crossref","first-page":"1047","DOI":"10.21437\/Interspeech.2009-322","volume-title":"Proceedings of Interspeech 2009","author":"D. Reynolds","year":"2009","unstructured":"D. Reynolds, P. Kenny, F. Castaldo, in Proceedings of Interspeech 2009. A study of new approaches to speaker diarization (ISCA(International Speech Communication Association)Brighton, 2009), pp. 1047\u20131050."},{"unstructured":"F. Valente, Variational bayesian methods for audio indexing. PhD thesis, Eurecom, Sophia-Antipolis, France (2005). http:\/\/dx.doi.org\/10.5075\/epfl-thesis-2092 . http:\/\/www.eurecom.fr\/publication\/1739 .","key":"154_CR5"},{"key":"154_CR6","doi-asserted-by":"publisher","first-page":"147","DOI":"10.21437\/Odyssey.2018-21","volume-title":"Odyssey The Speaker and Language Recognition Workshop","author":"M. Diez","year":"2018","unstructured":"M. Diez, P. M. L. Burget, in Odyssey The Speaker and Language Recognition Workshop. Speaker diarization based on bayesian hmm with eigenvoice priors (ISCALes Sables d\u2019Olonne, 2018), pp. 147\u2013154."},{"key":"154_CR7","doi-asserted-by":"publisher","first-page":"4809","DOI":"10.1109\/ICASSP.2015.7178884","volume-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"A. E. Bulut","year":"2015","unstructured":"A. E. Bulut, H. Demir, Y. Z. Isik, H. Erdogan, in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Plda-based diarization of telephone conversations (IEEEBrisbane, 2015), pp. 4809\u20134813. https:\/\/doi.org\/10.1109\/ICASSP.2015.7178884 ."},{"key":"154_CR8","volume-title":"Latent Structure Analysis","author":"P. F. Lazarsfeld","year":"1968","unstructured":"P. F. Lazarsfeld, N. W. Henry, Latent Structure Analysis (Houghton Mill, Boston, 1968)."},{"key":"154_CR9","first-page":"37","volume":"20","author":"J. Magidson","year":"2002","unstructured":"J. Magidson, J. K. Vermunt, Latent class models for clustering: A comparison with kmeans. Can. J. Mark. Res.20:, 37\u201344 (2002).","journal-title":"Can. J. Mark. Res."},{"key":"154_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/9780470567333","volume-title":"Latent Class and Latent Transition Analysis with Applications in the Social, Behavioral, and Health Sciences","author":"L. M. Collins","year":"2009","unstructured":"L. M. Collins, S. T. Lanza, Latent Class and Latent Transition Analysis with Applications in the Social, Behavioral, and Health Sciences, 1st edn. (Wiley, New York, 2009)."},{"key":"154_CR11","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.21437\/Interspeech.2007-516","volume-title":"Proceedings of Interspeech 2007","author":"K. J. Han","year":"2007","unstructured":"K. J. Han, S. S. Narayanan, in Proceedings of Interspeech 2007. A robust stopping criterion for agglomera-tive hierarchical clustering in a speaker diarization system (ISCAAntwerp, 2007), pp. 1853\u20131856."},{"unstructured":"NIST, The 2009 (RT-09) Rich Transcription Meeting Recognition Evaluation Plan (2009). Available: https:\/\/www.nist.gov\/itl\/iad\/mig\/rich-transcription-evaluation .","key":"154_CR12"},{"unstructured":"L. data consortium, LDC97S42, Catalog (1997). Available: http:\/\/www.ldc.upenn.edu\/Catalog\/catalogEntry.jsp?catalogIdDLDC97S42 . Accessed 29 Aug 2018.","key":"154_CR13"},{"issue":"1","key":"154_CR14","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/1687-4722-2012-19","volume":"2012","author":"M. Zelen\u00e1k","year":"2012","unstructured":"M. Zelen\u00e1k, H. Schulz, J. Hernando, Speaker diarization of broadcast news in albayzin 2010 evaluation campaign. EURASIP J. Audio Speech Music Process.2012(1), 19 (2012). https:\/\/doi.org\/10.1186\/1687-4722-2012-19 .","journal-title":"EURASIP J. Audio Speech Music Process."},{"volume-title":"The ICSI RT07s Speaker Diarization System","year":"2008","unstructured":"C. Wooters, M. Huijbregts, The ICSI RT07s Speaker Diarization System. (R. Stiefelhagen, R. Bowers, J. Fiscus, eds.) (Springer, Berlin, Heidelberg, 2008).","key":"154_CR15"},{"doi-asserted-by":"publisher","unstructured":"V. Gupta, G. Boulianne, P. Kenny, P. Ouellet, P. Dumouchel, in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing. Speaker diarization of french broadcast news, (2008), pp. 4365\u20134368. https:\/\/doi.org\/10.1109\/ICASSP.2008.4518622 .","key":"154_CR16","DOI":"10.1109\/ICASSP.2008.4518622"},{"key":"154_CR17","volume-title":"CMU SPUD Workshop","author":"S. Meignier","year":"2010","unstructured":"S. Meignier, T. Merlin, in CMU SPUD Workshop. Lium spkdiarization: an open source toolkit for diarization (HALDallas, 2010)."},{"key":"154_CR18","doi-asserted-by":"crossref","first-page":"3081","DOI":"10.21437\/Interspeech.2015-106","volume-title":"Proceedings of Interspeech 2015","author":"B. Desplanques","year":"2015","unstructured":"B. Desplanques, K. Demuynck, J. -P. Martens, in Proceedings of Interspeech 2015. Factor analysis for speaker segmentation and improved speaker diarization (ISCADresden, 2015), pp. 3081\u20133085."},{"issue":"4","key":"154_CR19","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/j.engappai.2009.01.012","volume":"22","author":"S. Jothilakshmi","year":"2009","unstructured":"S. Jothilakshmi, V. Ramalingam, S. Palanivel, Speaker diarization using auto associative neural networks. Eng. Appl. Artif. Intell.22(4), 667\u2013675 (2009). https:\/\/doi.org\/10.1016\/j.engappai.2009.01.012 .","journal-title":"Eng. Appl. Artif. Intell."},{"key":"154_CR20","doi-asserted-by":"publisher","first-page":"4420","DOI":"10.1109\/ICASSP.2015.7178806","volume-title":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"V. Gupta","year":"2015","unstructured":"V. Gupta, in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Speaker change point detection using deep neural nets (IEEEQueensland, 2015), pp. 4420\u20134424. https:\/\/doi.org\/10.1109\/ICASSP.2015.7178806 ."},{"key":"154_CR21","doi-asserted-by":"publisher","first-page":"4945","DOI":"10.1109\/ICASSP.2017.7953097","volume-title":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"M. Hruz","year":"2017","unstructured":"M. Hruz, Z. Zajic, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Convolutional neural network for speaker change detection in telephone speaker diarization system (IEEENew Orleans, 2017), pp. 4945\u20134949."},{"key":"154_CR22","doi-asserted-by":"publisher","first-page":"3562","DOI":"10.21437\/Interspeech.2017-51","volume-title":"Proceedings of Interspeech 2017","author":"Z. Zajic","year":"2017","unstructured":"Z. Zajic, M. Hruz, L. Muller, in Proceedings of Interspeech 2017. Speaker diarization using convolutional neural network for statistics accumulation refinement (ISCAStockholm, 2017), pp. 3562\u20133566."},{"key":"154_CR23","doi-asserted-by":"publisher","first-page":"5430","DOI":"10.1109\/ICASSP.2017.7953194","volume-title":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"H. Bredin","year":"2017","unstructured":"H. Bredin, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Tristounet: Triplet loss for speaker turn embedding (IEEENew Orleans, 2017), pp. 5430\u20135434."},{"key":"154_CR24","doi-asserted-by":"publisher","first-page":"3827","DOI":"10.21437\/Interspeech.2017-65","volume-title":"Proceedings of Interspeech 2017","author":"R. Yin","year":"2017","unstructured":"R. Yin, H. Bredin, C. Barras, in Proceedings of Interspeech 2017. Speaker change detection in broadcast tv using bidirectional long short-term memory networks (ISCAStockholm, 2017), pp. 3827\u20133831."},{"key":"154_CR25","doi-asserted-by":"publisher","first-page":"4958","DOI":"10.1109\/ICASSP.2010.5495088","volume-title":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S. Bozonnet","year":"2010","unstructured":"S. Bozonnet, N. W. D. Evans, C. Fredouille, in 2010 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). The lia-eurecom rt\u201909 speaker diarization system: Enhancements in speaker modelling and cluster purification (IEEEDallas, 2010), pp. 4958\u20134961. https:\/\/doi.org\/10.1109\/ICASSP.2010.5495088 ."},{"key":"154_CR26","first-page":"138","volume-title":"Odyssey The Speaker and Language Recognition Workshop","author":"I. Lapidot","year":"2012","unstructured":"I. Lapidot, J. -F. Bonastre, in Odyssey The Speaker and Language Recognition Workshop. On the importance of efficient transition modeling for speaker diarization (ISCASingapore, 2012), pp. 138\u2013145."},{"key":"154_CR27","doi-asserted-by":"publisher","first-page":"2190","DOI":"10.21437\/Interspeech.2016-503","volume-title":"Proceedings of Interspeech 2016","author":"I. Lapidot","year":"2016","unstructured":"I. Lapidot, J. -F. Bonastre, in Proceedings of Interspeech 2016. On the importance of efficient transition modeling for speaker diarization (ISCASan Francisco, 2016), pp. 2190\u20132193."},{"key":"154_CR28","doi-asserted-by":"publisher","first-page":"2185","DOI":"10.21437\/Interspeech.2016-126","volume-title":"Proceedings of Interspeech 2016","author":"R. Milner","year":"2016","unstructured":"R. Milner, T. Hain, in Proceedings of Interspeech 2016. Dnn-based speaker clustering for speaker diarisation (ISCASan Francisco, 2016), pp. 2185\u20132189."},{"key":"154_CR29","doi-asserted-by":"publisher","first-page":"5450","DOI":"10.1109\/ICASSP.2017.7953198","volume-title":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"M. Najafian","year":"2017","unstructured":"M. Najafian, J. H. L. Hansen, in 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Environment aware speaker diarization for moving targets using parallel dnn-based recognizers (IEEENew Orleans, 2017), pp. 5450\u20135454. https:\/\/doi.org\/10.1109\/ICASSP.2017.7953198 ."},{"key":"154_CR30","doi-asserted-by":"crossref","first-page":"2441","DOI":"10.21437\/Interspeech.2005-651","volume-title":"Proceedings of Interspeech 2005","author":"X. Zhu","year":"2005","unstructured":"X. Zhu, C. Barras, S. Meignier, J. -L. Gauvain, in Proceedings of Interspeech 2005. Combining speaker identification and bic for speaker diarization (ISCALisbon, 2005), pp. 2441\u20132444."},{"key":"154_CR31","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.21437\/Interspeech.2010-440","volume-title":"Proceedings of Interspeech 2010","author":"T. L. Nwe","year":"2010","unstructured":"T. L. Nwe, H. Sun, B. Ma, H. Li, in Proceedings of Interspeech 2010. Speaker diarization in meeting audio for single distant microphone (ISCAMakuhari, 2010), pp. 1505\u20131508."},{"issue":"2","key":"154_CR32","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/TASL.2011.2158419","volume":"20","author":"G. Friedland","year":"2012","unstructured":"G. Friedland, A. Janin, D. Imseng, X. Anguera, L. Gottlieb, M. Huijbregts, M. T. Knox, O. Vinyals, The icsi rt-09 speaker diarization system. IEEE Trans. Audio Speech Lang. Process.20(2), 371\u2013381 (2012). https:\/\/doi.org\/10.1109\/TASL.2011.2158419 .","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"154_CR33","doi-asserted-by":"crossref","first-page":"945","DOI":"10.21437\/Interspeech.2011-383","volume-title":"Proceedings of Interspeech 2011","author":"S. Shum","year":"2011","unstructured":"S. Shum, N. Dehak, E. Chuangsuwanich, D. Reynolds, J. Glass, in Proceedings of Interspeech 2011. Exploiting intra-conversation variability for speaker diarization (ISCAFlorence, 2011), pp. 945\u2013948."},{"doi-asserted-by":"publisher","unstructured":"G. Sell, D. Garcia-Romero, in 2014 IEEE Spoken Language Technology Workshop (SLT). Speaker diarization with plda i-vector scoring and unsupervised calibration (IEEE, 2014), pp. 413\u2013417. https:\/\/doi.org\/10.1109\/SLT.2014.7078610 .","key":"154_CR34","DOI":"10.1109\/SLT.2014.7078610"},{"key":"154_CR35","doi-asserted-by":"publisher","first-page":"2175","DOI":"10.21437\/Interspeech.2016-572","volume-title":"Proceedings of Interspeech 2016","author":"G. L. Lan","year":"2016","unstructured":"G. L. Lan, D. Charlet, A. Larcher, S. Meignier, in Proceedings of Interspeech 2016. Iterative plda adaptation for speaker diarization (ISCASan Francisco, 2016), pp. 2175\u20132179."},{"key":"154_CR36","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/ICASSP.2014.6853567","volume-title":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"A. Sholokhov","year":"2014","unstructured":"A. Sholokhov, T. Pekhovsky, O. Kudashev, A. Shulipa, T. Kinnunen, in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Bayesian analysis of similarity matrices for speaker diarization (IEEEFlorence, 2014), pp. 106\u2013110."},{"key":"154_CR37","doi-asserted-by":"publisher","first-page":"5045","DOI":"10.1109\/ICASSP.2016.7472638","volume-title":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"W. Zhu","year":"2016","unstructured":"W. Zhu, J. Pelecanos, in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Online speaker diarization using adapted i-vector transforms (IEEEShanghai, 2016), pp. 5045\u20135049. https:\/\/doi.org\/10.1109\/ICASSP.2016.7472638 ."},{"issue":"10","key":"154_CR38","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1109\/TASL.2013.2264673","volume":"21","author":"S. H. Shum","year":"2013","unstructured":"S. H. Shum, N. Dehak, R. Dehak, J. R. Glass, Unsupervised methods for speaker diarization: an integrated and iterative approach. IEEE Trans. Audio Speech Lang. Process.21(10), 2015\u20132028 (2013). https:\/\/doi.org\/10.1109\/TASL.2013.2264673 .","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"154_CR39","doi-asserted-by":"publisher","first-page":"2194","DOI":"10.21437\/Interspeech.2016-1380","volume-title":"Proceedings of Interspeech 2016","author":"G. Sell","year":"2016","unstructured":"G. Sell, A. McCree, D. Garcia-Romero, in Proceedings of Interspeech 2016. Priors for speaker counting and diarization with ahc (ISCASan Francisco, 2016), pp. 2194\u20132198."},{"issue":"2","key":"154_CR40","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1109\/TASL.2011.2159710","volume":"20","author":"N. Evans","year":"2012","unstructured":"N. Evans, S. Bozonnet, D. Wang, C. Fredouille, R. Troncy, A comparative study of bottom-up and top-down approaches to speaker diarization. IEEE\/ACM Trans. Audio, Speech, Lang. Process.20(2), 382\u2013392 (2012).","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"issue":"2","key":"154_CR41","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1109\/TASL.2011.2159203","volume":"20","author":"T. L. Nwe","year":"2012","unstructured":"T. L. Nwe, H. Sun, B. Ma, H. Li, Speaker clustering and cluster purification methods for rt07 and rt09 evaluation meeting data. Audio Speech Lang. Process. IEEE Trans.20(2), 461\u2013473 (2012). https:\/\/doi.org\/10.1109\/TASL.2011.2159203 .","journal-title":"Audio Speech Lang. Process. IEEE Trans."},{"issue":"4","key":"154_CR42","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N. Dehak","year":"2011","unstructured":"N. Dehak, P. J. Kenny, R. Dehak, P. Dumouchel, P. Ouellet, Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process.19(4), 788\u2013798 (2011). https:\/\/doi.org\/10.1109\/TASL.2010.2064307 .","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"154_CR43","volume-title":"Tables of Integrals, Series, and Products","author":"I. S. Gradshteyn","year":"2000","unstructured":"I. S. Gradshteyn, I. M. Ryzhik, Tables of Integrals, Series, and Products, 7th ed. (Academic Press, San Diego, 2000)."},{"key":"154_CR44","doi-asserted-by":"crossref","first-page":"249","DOI":"10.21437\/Interspeech.2011-53","volume-title":"Proceedings of Interspeech 2011","author":"D. Garcia-Romero","year":"2011","unstructured":"D. Garcia-Romero, C. Espy-Wilson, in Proceedings of Interspeech 2011. Analysis of i-vector length normalization in speaker recognition systems (ISCAFlorence, 2011), pp. 249\u2013252."},{"key":"154_CR45","first-page":"194","volume-title":"Odyssey The Speaker and Language Recognition Workshop","author":"N. Br\u00fcmmer","year":"2010","unstructured":"N. Br\u00fcmmer, E. D. Villiers, in Odyssey The Speaker and Language Recognition Workshop. The speaker partitioning problem (ISCABrno, 2010), pp. 194\u2013201."},{"key":"154_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICCV.2007.4409052","volume-title":"2007 IEEE 11th International Conference on Computer Vision","author":"S. J. D. Prince","year":"2007","unstructured":"S. J. D. Prince, J. H. Elder, in 2007 IEEE 11th International Conference on Computer Vision. Probabilistic linear discriminant analysis for inferences about identity (IEEERio de Janeiro, 2007), pp. 1\u20138. https:\/\/doi.org\/10.1109\/ICCV.2007.4409052 ."},{"key":"154_CR47","first-page":"4057","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"D. Povey","year":"2008","unstructured":"D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, K. Visweswariah, in IEEE International Conference on Acoustics, Speech and Signal Processing. Boosted mmi for model and feature-space discriminative training (IEEELas Vegas, 2008), pp. 4057\u20134060."},{"issue":"441-458","key":"154_CR48","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1098\/rsta.1909.0016","volume":"209","author":"M. J","year":"1909","unstructured":"M. J, Xvi. functions of positive and negative type, and their connection the theory of integral equations. Philos. Trans. R. Soc. Lond. A Math. Phys. Eng. Sci.209(441-458), 415\u2013446 (1909). https:\/\/doi.org\/10.1098\/rsta.1909.0016 . http:\/\/rsta.royalsocietypublishing.org\/content\/209\/441-458\/415.full.pdf .","journal-title":"Philos. Trans. R. Soc. Lond. A Math. Phys. Eng. Sci."},{"key":"154_CR49","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1145\/1015330.1015424","volume-title":"Proceedings of the Twenty-first International Conference on Machine Learning. ICML \u201904","author":"F. R. Bach","year":"2004","unstructured":"F. R. Bach, G. R. G. Lanckriet, M. I. Jordan, in Proceedings of the Twenty-first International Conference on Machine Learning. ICML \u201904. Multiple kernel learning, conic duality, and the smo algorithm (ACMNew York, 2004), p. 6. https:\/\/doi.org\/10.1145\/1015330.1015424 . http:\/\/doi.acm.org\/10.1145\/1015330.1015424 ."},{"key":"154_CR50","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-3166-0","volume-title":"Random Point Processes in Time and Space","author":"D. L. Snyder","year":"1991","unstructured":"D. L. Snyder, M. I. Miller, Random Point Processes in Time and Space (Springer, New York, 1991). https:\/\/doi.org\/10.1007\/978-1-4612-3166-0 ."},{"key":"154_CR51","volume-title":"IEEE Workshop on Signal Processing Systems (SIPS)","author":"L. He","year":"2017","unstructured":"L. He, X. Chen, C. Xu, Tianyu, J. Liu, in IEEE Workshop on Signal Processing Systems (SIPS). Ivec-plda-ahc priors for vb-hmm speaker diarization system (IEEELorient, 2017)."},{"issue":"7","key":"154_CR52","doi-asserted-by":"publisher","first-page":"2011","DOI":"10.1109\/TASL.2007.902460","volume":"15","author":"X. Anguera","year":"2007","unstructured":"X. Anguera, C. Wooters, J. Hernando, Acoustic beamforming for speaker diarization of meetings. IEEE Trans. Audio Speech Lang. Process.15(7), 2011\u20132022 (2007). https:\/\/doi.org\/10.1109\/TASL.2007.902460 .","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"154_CR53","first-page":"4","volume-title":"Proc. ICSLP","author":"A. Adami","year":"2002","unstructured":"A. Adami, L. Burget, S. Dupont, H. Garudadri, F. Grezl, H. Hermansky, P. Jain, S. Kajarekar, N. Morgan, S. Sivadas, in Proc. ICSLP. Qualcomm-icsi-ogi features for asr (ISCADenver, 2002), pp. 4\u20137."},{"key":"154_CR54","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/ICASSP.2014.6853565","volume-title":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"S. H. Yella","year":"2014","unstructured":"S. H. Yella, H. Bourlard, in 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Information bottleneck based speaker diarization of meetings using non-speech as side information (IEEEFlorence, 2014), pp. 96\u2013100. https:\/\/doi.org\/10.1109\/ICASSP.2017.7953097 ."},{"key":"154_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.csl.2017.01.011","volume":"45","author":"I. Lapidot","year":"2017","unstructured":"I. Lapidot, A. Shoa, T. Furmanov, L. Aminov, A. Moyal, J. -F. Bonastre, Generalized viterbi-based models for time-series segmentation and clustering applied to speaker diarization. Comput. Speech Lang.45:, 1\u201320 (2017).","journal-title":"Comput. Speech Lang."},{"key":"154_CR56","first-page":"411","volume":"45","author":"Z. Zajic","year":"2016","unstructured":"Z. Zajic, M. Kunesova, V. Radova, Investigation of segmentation in i-vector based speaker diarization of telephone speech. Springer Int. Publ.45:, 411\u2013418 (2016).","journal-title":"Springer Int. Publ."},{"key":"154_CR57","first-page":"4133","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"F. Castaldo","year":"2008","unstructured":"F. Castaldo, D. Colibro, E. Dalmasso, P. Laface, C. Vair, in IEEE International Conference on Acoustics, Speech and Signal Processing. Stream-based speaker segmentation using speaker factors and eigenvoices (IEEELas Vegas, 2008), pp. 4133\u20134136."},{"issue":"1","key":"154_CR58","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/TASLP.2013.2285474","volume":"22","author":"M. Senoussaoui","year":"2013","unstructured":"M. Senoussaoui, P. Kenny, T. Stafylakis, P. Dumouchel, A study of the cosine distance-based mean shift for telephone speech diarization. IEEE\/ACM Trans. Audio Speech Lang. Process.22(1), 217\u2013227 (2013).","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"154_CR59","volume-title":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding","author":"D. Povey","year":"2011","unstructured":"D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, P. Motlicek, Y. Qian, P. Schwarz, J. Silovsky, G. Stemmer, K. Vesely, in IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. The kaldi speech recognition toolkit (IEEEWaikoloa, 2011). IEEE Catalog No.: CFP11SRW-USB."},{"issue":"4","key":"154_CR60","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TASL.2012.2236317","volume":"21","author":"C. Vaquero","year":"2013","unstructured":"C. Vaquero, A. Ortega, A. Miguel, E. Lleida, Quality assessment for speaker diarization and its application in speaker characterization. IEEE Trans. Audio Speech Lang. Process.21(4), 816\u2013827 (2013).","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"154_CR61","doi-asserted-by":"crossref","first-page":"4213","DOI":"10.1109\/ICASSP.2009.4960558","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"E. Dalmasso","year":"2009","unstructured":"E. Dalmasso, F. Castaldo, P. Laface, D. Colibro, C. Vair, in IEEE International Conference on Acoustics, Speech and Signal Processing. Loquendo - politecnico di torino\u2019s 2008 nist speaker recognition evaluation system (IEEETaipei, 2009), pp. 4213\u20134216."},{"key":"154_CR62","first-page":"4213","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing","author":"F. Castaldo","year":"2011","unstructured":"F. Castaldo, D. Colibro, C. Vair, S. Cumani, P. Laface, in IEEE International Conference on Acoustics, Speech and Signal Processing. Loquendo - politecnico di torino\u2019s 2010 nist speaker recognition evaluation system (IEEEPrague, 2011), pp. 4213\u20134216."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0154-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13636-019-0154-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13636-019-0154-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T03:03:23Z","timestamp":1695006203000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/s13636-019-0154-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,9]]},"references-count":62,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["154"],"URL":"https:\/\/doi.org\/10.1186\/s13636-019-0154-z","relation":{},"ISSN":["1687-4722"],"issn-type":[{"type":"electronic","value":"1687-4722"}],"subject":[],"published":{"date-parts":[[2019,7,9]]},"assertion":[{"value":"29 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"12"}}