{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T00:02:38Z","timestamp":1724716958281},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T00:00:00Z","timestamp":1616371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s00034-021-01660-6","type":"journal-article","created":{"date-parts":[[2021,3,22]],"date-time":"2021-03-22T04:15:48Z","timestamp":1616386548000},"page":"3996-4017","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Rapid Speaker Adaptation Based on Combination of KPCA and Latent Variable Model"],"prefix":"10.1007","volume":"40","author":[{"given":"Zohreh","family":"Ansari","sequence":"first","affiliation":[]},{"given":"Farshad","family":"Almasganj","sequence":"additional","affiliation":[]},{"given":"Seyed Jahanshah","family":"Kabudian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,22]]},"reference":[{"key":"1660_CR1","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1006\/csla.1997.0031","volume":"11","author":"SM Ahadi","year":"1997","unstructured":"S.M. Ahadi, P.C. Woodland, Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 11, 187\u2013206 (1997)","journal-title":"Comput. Speech Lang."},{"key":"1660_CR2","doi-asserted-by":"crossref","unstructured":"Z. Ansari, F. Almasganj, Implementing PCA-based speaker adaptation methods in a Persian ASR system, in Proceeding of 5th International Symposium on Telecommunications (IST 2010) (2010)","DOI":"10.1109\/ISTEL.2010.5734126"},{"key":"1660_CR3","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.sbspro.2012.01.020","volume":"32","author":"Z Ansari","year":"2012","unstructured":"Z. Ansari, F. Almasganj, Implementing KPCA-based speaker adaptation methods with different optimization algorithms in a Persian ASR system. Procedia Soc. Behav. Sci. 32, 117\u2013127 (2012)","journal-title":"Procedia Soc. Behav. Sci."},{"key":"1660_CR4","doi-asserted-by":"publisher","DOI":"10.1002\/0471787779","volume-title":"Nonlinear Programming, Theory and Algorithms","author":"MS Bazarra","year":"2006","unstructured":"M.S. Bazarra, H.D. Sherali, C.M. Shelty, Nonlinear Programming, Theory and Algorithms (Wiley, New York, 2006)."},{"key":"1660_CR5","unstructured":"M. Bijankhan, M.J. Sheikhzadegan, FARSDAT-the Farsi spoken language database, in Proceedings of International Conference on Speech Sciences and Technology, Vol. 2, (1994), pp. 826\u2013829"},{"key":"1660_CR6","doi-asserted-by":"crossref","unstructured":"C.M. Bishop, Latent variable models, in Learning in Graphical Models (Springer, Dordrecht, 1998), pp. 371\u2013403","DOI":"10.1007\/978-94-011-5014-9_13"},{"key":"1660_CR7","unstructured":"M.A. Carreira-Perpin\u00e0n, Continuous Latent Variable Models for Dimensionality Reduction and Sequential Data Reconstruction. PhD Thesis (Department of Computer Science, University of Sheffield, UK, 2001)"},{"key":"1660_CR8","unstructured":"M.A. Carreira-Perpin\u00e1n, Z. Lu, The Laplacian eigenmaps latent variable model, in Proceeding of Artificial Intelligence and Statistics (2007), pp. 59\u201366"},{"key":"1660_CR9","unstructured":"K.T. Chen, W.W. Liau, H.M. Wang, L.S. Lee, Fast speaker adaptation using eigenspace-based maximum likelihood linear regression, in Proceedings of International Conference on Spoken Language Processing (2000), pp. 742\u2013745"},{"key":"1660_CR10","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.engappai.2015.01.010","volume":"40","author":"DJ Choi","year":"2015","unstructured":"D.J. Choi, J.S. Park, Y.H. Oh, Unsupervised rapid speaker adaptation based on selective eigenvoice merging for user-specific voice interaction. Eng. Appl. Artif. Intell. 40, 95\u2013102 (2015)","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"1660_CR11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"AP Dempster","year":"1977","unstructured":"A.P. Dempster, N.M. Laird, D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. B 39(1), 1\u201338 (1977)","journal-title":"J. R. Stat. Soc. B"},{"issue":"7","key":"1660_CR12","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1016\/j.crme.2018.04.011","volume":"346","author":"P D\u00edez","year":"2018","unstructured":"P. D\u00edez, S. Zlotnik, A. Garc\u00eda-Gonz\u00e1lez, A. Huerta, Algebraic PGD for tensor separation and compression: an algorithmic approach. Comptes Rendus M\u00e9canique 346(7), 501\u2013514 (2018)","journal-title":"Comptes Rendus M\u00e9canique"},{"key":"1660_CR13","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1006\/csla.1996.0013","volume":"10","author":"MJF Gales","year":"1996","unstructured":"M.J.F. Gales, P.C. Woodland, Mean and variance adaptation within the MLLR framework. Comput. Speech Lang. 10, 249\u2013264 (1996)","journal-title":"Comput. Speech Lang."},{"key":"1660_CR14","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/89.848223","volume":"8","author":"MJF Gales","year":"2000","unstructured":"M.J.F. Gales, Cluster adaptive training of hidden Markov models. IEEE Trans. Speech Audio Process. 8, 417\u2013428 (2000)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"1660_CR15","doi-asserted-by":"crossref","unstructured":"A. Garc\u00eda-Gonz\u00e1lez, A. Huerta, S. Zlotnik, P. D\u00edez, A kernel Principal Component Analysis (kPCA) digest with a new backward mapping (pre-image reconstruction) strategy (2020). arXiv preprint arXiv:2001.01958","DOI":"10.21203\/rs.3.rs-126052\/v1"},{"key":"1660_CR16","doi-asserted-by":"crossref","unstructured":"J.S. Garofolo, L.F.Lamel, W.M. Fisher, J.G. Fiscus, D.S. Pallett, DARPA TIMIT acoustic-phonetic continuous speech corpus CD-ROM, in NIST Speech Disc 1\u20131.1. STIN, 93 (1993), p. 27403","DOI":"10.6028\/NIST.IR.4930"},{"key":"1660_CR17","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"J-L Gauvain","year":"1994","unstructured":"J.-L. Gauvain, C.-H. Lee, Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 2, 291\u2013298 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1","key":"1660_CR18","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s11831-016-9173-4","volume":"25","author":"D Gonz\u00e1lez","year":"2018","unstructured":"D. Gonz\u00e1lez, J.V. Aguado, E. Cueto, E. Abisset-Chavanne, F. Chinesta, kPCA-based parametric solutions within the PGD framework. Arch. Comput. Methods Eng. 25(1), 69\u201386 (2018)","journal-title":"Arch. Comput. Methods Eng."},{"issue":"10","key":"1660_CR19","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.1016\/j.medengphy.2014.06.021","volume":"36","author":"L Grassi","year":"2014","unstructured":"L. Grassi, E. Schileo, C. Boichon, M. Viceconti, F. Taddei, Comprehensive evaluation of PCA-based finite element modelling of the human femur. Med. Eng. Phys. 36(10), 1246\u20131252 (2014)","journal-title":"Med. Eng. Phys."},{"key":"1660_CR20","doi-asserted-by":"crossref","unstructured":"S. Hahm, Y. Ohkawa, M. Ito, M. Suzuki, A. Ito, S. Makino, Aspect-model based referenced speaker weighting, in Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP2010) (2010), pp. 4302\u20134305","DOI":"10.1109\/ICASSP.2010.5495672"},{"key":"1660_CR21","doi-asserted-by":"crossref","unstructured":"T. Hazen, J. Glass, A Comparison of novel techniques for instantaneous speaker adaptation, in Proceedings of Eurospeech, Greece (1997)","DOI":"10.21437\/Eurospeech.1997-542"},{"key":"1660_CR22","unstructured":"R.W.H. Hsiao, Kernel Eigenspace Based MLLR Adaptation. Master Thesis, Department of Computer Science, Hong Kong University (2004)"},{"key":"1660_CR23","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"X Hung","year":"2001","unstructured":"X. Hung, A. Acero, H.-W. Hon, Spoken Language Processing: A Guide to Theory, Algorithm, and System Development (Prentice Hall, NJ, 2001)."},{"key":"1660_CR24","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1016\/j.specom.2010.04.005","volume":"52","author":"A Jafari","year":"2010","unstructured":"A. Jafari, F. Almasganj, Using Laplacian eigenmaps latent variable model and manifold learning to improve speech recognition accuracy. J. Speech Commun. 52, 725\u2013735 (2010)","journal-title":"J. Speech Commun."},{"key":"1660_CR25","doi-asserted-by":"crossref","unstructured":"Y. Jeong, Speaker adaptation based on the multilinear decompositions of training speaker models, in Proceedings of International Conference on Acoustics, Speech and Signal Processing (ICASSP2010), Dallas, TX (2010), pp. 4870\u20134873","DOI":"10.1109\/ICASSP.2010.5495117"},{"issue":"8","key":"1660_CR26","doi-asserted-by":"publisher","first-page":"2352","DOI":"10.1109\/TASL.2012.2202649","volume":"20","author":"Y Jeong","year":"2012","unstructured":"Y. Jeong, Adaptation of hidden Markov models using model-as-matrix representation. IEEE Trans. Audio Speech Lang. Process. 20(8), 2352\u20132364 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1660_CR27","volume-title":"Principal Component Analysis","author":"IT Jolliffe","year":"2002","unstructured":"I.T. Jolliffe, Principal Component Analysis (Springer, New York, 2002)."},{"key":"1660_CR28","doi-asserted-by":"crossref","unstructured":"S. Keyhanian, B. Nasersharif, Laplacian eigenmaps latent variable model modification for pattern recognition, in Proceeding of the 23rd of Iranian Conference on Electrical Engineering (2015), pp. 668\u2013673","DOI":"10.1109\/IranianCEE.2015.7146298"},{"issue":"2","key":"1660_CR29","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/LSP.2010.2097591","volume":"18","author":"NS Kim","year":"2011","unstructured":"N.S. Kim, J.S. Sung, D.H. Hong, Factored MLLR adaptation. IEEE Signal Process. Lett. 18(2), 99\u2013102 (2011)","journal-title":"IEEE Signal Process. Lett."},{"key":"1660_CR30","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1109\/89.876308","volume":"14","author":"R Kuhn","year":"2000","unstructured":"R. Kuhn, J.-C. Junqua, P. Nguyen, N. Niedzeiki, Rapid speaker adaptation in eigenvoice space. IEEE Trans. Speech Audio Process. 14, 695\u2013707 (2000)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"1660_CR31","unstructured":"J.T. Kwok, I.W. Tsang, The pre-image problem in kernel methods, in Proceedings of the International Conference on Machine Learning (ICML 2003), Washington, DC (2003)"},{"key":"1660_CR32","first-page":"371641","volume":"66","author":"KF Lee","year":"1989","unstructured":"K.F. Lee, H.W. Hon, Speaker-independent phone recognition using hidden Markov models. IEEE Trans. Acoust. Speech Signal Process. 66, 371641\u20131648 (1989)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"1","key":"1660_CR33","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s11831-016-9172-5","volume":"25","author":"E Lopez","year":"2018","unstructured":"E. Lopez, D. Gonzalez, J.V. Aguado, E. Abisset-Chavanne, E. Cueto, C. Binetruy, F. Chinesta, A manifold learning approach for integrated computational materials engineering. Arch. Comput. Methods Eng. 25(1), 59\u201368 (2018)","journal-title":"Arch. Comput. Methods Eng."},{"key":"1660_CR34","unstructured":"Z. Lu, C. Sminchisescu, M.\u00c1. Carreira-Perpi\u00f1\u00e1n, People tracking with the laplacian eigenmaps latent variable model, in Proceeding of Advances in Neural Information Processing Systems (2008), pp. 1705\u20131712"},{"key":"1660_CR35","doi-asserted-by":"publisher","first-page":"984","DOI":"10.1109\/TSA.2005.851971","volume":"13","author":"B Mak","year":"2005","unstructured":"B. Mak, J.T. Kwok, S. Ho, Kernel eigenvoice speaker adaptation. IEEE Trans. Audio Speech Lang. Process. 13, 984\u2013992 (2005)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1660_CR36","doi-asserted-by":"publisher","first-page":"1267","DOI":"10.1109\/TSA.2005.860836","volume":"14","author":"B Mak","year":"2006","unstructured":"B. Mak, R.W.-H. Hsiao, S.K.-L. Ho, J.T. Kwok, Embedded kernel eigenvoice speaker adaptation and its implication to reference speaker weighting. IEEE Trans. Audio Speech Lang. Process. 14, 1267\u20131280 (2006)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"1660_CR37","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1109\/TASL.2006.885941","volume":"15","author":"B Mak","year":"2007","unstructured":"B. Mak, R.W.-H. Hsiao, Kernel eigen-space-based MLLR adaptation. IEEE Trans. Audio Speech Lang. Process. 15, 784\u2013795 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"7","key":"1660_CR38","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TASL.2009.2019920","volume":"17","author":"BK-W Mak","year":"2009","unstructured":"B.K.-W. Mak, T.-C. Lai, I.W. Tsang, J.T.-Y. Kwok, Maximum penalized likelihood kernel regression for fast adaptation. IEEE Trans Audio Speech Lang. Process. 17(7), 1372\u20131381 (2009)","journal-title":"IEEE Trans Audio Speech Lang. Process."},{"key":"1660_CR39","volume-title":"The EM Algorithm and Extensions","author":"GJ McLachlan","year":"1996","unstructured":"G.J. McLachlan, T. Krishnan, The EM Algorithm and Extensions (Wiley, New York, 1996)."},{"key":"1660_CR40","doi-asserted-by":"crossref","unstructured":"Y. Miao, F. Metze, A. Waibel, Learning discriminative basis coefficients for eigenspace MLLR unsupervised adaptation, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (2013), pp. 7927\u20137931","DOI":"10.1109\/ICASSP.2013.6639208"},{"issue":"5","key":"1660_CR41","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1080\/00207160802044118","volume":"87","author":"Y Pang","year":"2010","unstructured":"Y. Pang, L. Wang, Y. Yuan, Generalized KPCA by adaptive rules in feature space. Intern. J. Comput. Math. 87(5), 956\u2013968 (2010)","journal-title":"Intern. J. Comput. Math."},{"issue":"12","key":"1660_CR42","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1109\/LSP.2011.2171681","volume":"18","author":"Z Roupakia","year":"2011","unstructured":"Z. Roupakia, M. Gales, Kernel eigenvoices (revisited) for large-vocabulary speech recognition. IEEE Signal Process. Lett. 18(12), 709\u2013712 (2011)","journal-title":"IEEE Signal Process. Lett."},{"key":"1660_CR43","doi-asserted-by":"crossref","unstructured":"Z. Roupakia, A. Ragni, M. Gales, Rapid nonlinear speaker adaptation for large-vocabulary continuous speech recognition, in Proceedings of INTERSPEECH 2012, Portland, Oregon (2012)","DOI":"10.21437\/Interspeech.2012-486"},{"key":"1660_CR44","doi-asserted-by":"crossref","unstructured":"O. Saz, T. Hain, Using contextual information in joint factor eigenspace MLLR for speech recognition in diverse scenarios, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014), pp. 6314\u20136318","DOI":"10.1109\/ICASSP.2014.6854819"},{"issue":"5","key":"1660_CR45","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1162\/089976698300017467","volume":"10","author":"B Sch\u00f6lkopf","year":"1998","unstructured":"B. Sch\u00f6lkopf, K.-R. M\u00fcller, Nonlinear component analysis as a kernel eigenvalue problem. J. Neural Comput. 10(5), 1299\u20131319 (1998)","journal-title":"J. Neural Comput."},{"issue":"1","key":"1660_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-20121-w","volume":"8","author":"Y Shiokawa","year":"2018","unstructured":"Y. Shiokawa, Y. Date, J. Kikuchi, Application of kernel principal component analysis and computational machine learning to exploration of metabolites strongly associated with diet. Sci. Rep. 8(1), 1\u20138 (2018)","journal-title":"Sci. Rep."},{"key":"1660_CR47","doi-asserted-by":"crossref","unstructured":"J.C. Snyder, S. Mika, K. Burke, K.R. M\u00fcller, Kernels, pre-images and optimization, in Empirical Inference (Springer, Berlin, 2013), pp. 245\u2013259","DOI":"10.1007\/978-3-642-41136-6_21"},{"issue":"3","key":"1660_CR48","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1109\/TASL.2008.916530","volume":"16","author":"Y Tang","year":"2008","unstructured":"Y. Tang, R. Rose, Rapid speaker adaptation using clustered maximum-likelihood linear basis with sparse training data. J. IEEE Trans. Audio Speech Lang. Process. 16(3), 607\u2013616 (2008)","journal-title":"J. IEEE Trans. Audio Speech Lang. Process."},{"key":"1660_CR49","unstructured":"Q. Wang, Kernel principal component analysis and its applications in face recognition and active shape models (2012). arXiv preprint arXiv:1207.3538"},{"issue":"4","key":"1660_CR50","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TBME.2012.2186448","volume":"59","author":"D Widjaja","year":"2012","unstructured":"D. Widjaja, C. Varon, A. Dorado, J.A. Suykens, S. Van Huffel, Application of kernel principal component analysis for single-lead-ECG-derived respiration. IEEE. Trans. Biomed. Eng. 59(4), 1169\u20131176 (2012)","journal-title":"IEEE. Trans. Biomed. Eng."},{"key":"1660_CR51","unstructured":"Young et al., HTK Book (2009). http:\/\/htk.eng.cam.ac.uk"},{"issue":"4","key":"1660_CR52","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1109\/TNN.2009.2039647","volume":"21","author":"WS Zheng","year":"2010","unstructured":"W.S. Zheng, J. Lai, P.C. Yuen, Penalized preimage learning in kernel principal component analysis. IEEE Trans. Neural Netw. 21(4), 551\u2013570 (2010)","journal-title":"IEEE Trans. Neural Netw."}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-021-01660-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-021-01660-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-021-01660-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T13:54:22Z","timestamp":1724680462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-021-01660-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,22]]},"references-count":52,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["1660"],"URL":"https:\/\/doi.org\/10.1007\/s00034-021-01660-6","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"type":"print","value":"0278-081X"},{"type":"electronic","value":"1531-5878"}],"subject":[],"published":{"date-parts":[[2021,3,22]]},"assertion":[{"value":"23 October 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with Ethical Standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}