{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T04:26:34Z","timestamp":1688444794638},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,8,16]],"date-time":"2013-08-16T00:00:00Z","timestamp":1376611200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1007\/s11265-013-0785-8","type":"journal-article","created":{"date-parts":[[2013,8,15]],"date-time":"2013-08-15T14:33:51Z","timestamp":1376577231000},"page":"341-358","source":"Crossref","is-referenced-by-count":8,"title":["Structural Bayesian Linear Regression for Hidden Markov Models"],"prefix":"10.1007","volume":"74","author":[{"given":"Shinji","family":"Watanabe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biing-Hwang","family":"Juang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,8,16]]},"reference":[{"key":"785_CR1","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"CJ Leggetter","year":"1995","unstructured":"Leggetter, C.J., & Woodland, P.C. (1995). Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech and Language, 9, 171\u2013185.","journal-title":"Computer Speech and Language"},{"key":"785_CR2","doi-asserted-by":"crossref","unstructured":"Digalakis, V., Ritischev, D., Neumeyer, L. (1995). Speaker adaptation using constrained reestimation of Gaussian mixtures. IEEE Transactions on Speech and Audio Processing, 3, 357\u2013366.","DOI":"10.1109\/89.466659"},{"key":"785_CR3","unstructured":"Lee, C.-H., & Huo, Q. (2000). On adaptive decision rules and decision parameter adaptation for automatic speech recognition. In Proceedings of the IEEE (Vol. 88, pp. 1241\u20131269)."},{"issue":"9","key":"785_CR4","doi-asserted-by":"crossref","first-page":"2348","DOI":"10.1587\/transinf.E93.D.2348","volume":"93","author":"K Shinoda","year":"2010","unstructured":"Shinoda, K. (2010). Acoustic model adaptation for speech recognition. IEICE Transactions on Information and Systems, 93(9), 2348\u20132362.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"785_CR5","doi-asserted-by":"crossref","unstructured":"Sankar, A., & Lee, C.-H. (1996). A maximum-likelihood approach to stochastic matching for robust speech recognition. IEEE Transactions on Speech and Audio Processing, 4(3), 190\u2013202.","DOI":"10.1109\/89.496215"},{"key":"785_CR6","unstructured":"Chien, J.-T., Lee, C.-H., Wang, H.-C. (1997). Improved bayesian learning of hidden Markov models for speaker adaptation. In Processing of ICASSP (Vol. 2, pp. 1027\u20131030). IEEE"},{"key":"785_CR7","doi-asserted-by":"crossref","unstructured":"Chen, K.-T., Liau, W.-W., Wang, H.-W., Lee, L.-S. (2000). Fast speaker adaptation using eigenspace-based maximum likelihood linear regression. In Proceedings of ICSLP (Vol. 3, pp. 742\u2013745).","DOI":"10.21437\/ICSLP.2000-642"},{"issue":"5","key":"785_CR8","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1109\/TSA.2005.851971","volume":"13","author":"B Mak","year":"2005","unstructured":"Mak, B., Kwok, J.T., Ho, S. (2005). Kernel eigenvoice speaker adaptation. IEEE Transactions on Speech and Audio Processing, 13(5), 984\u2013992.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"785_CR9","doi-asserted-by":"crossref","unstructured":"Delcroix, M., Nakatani, T., Watanabe, S. (2009). Static and dynamic variance compensation for recognition of reverberant speech with dereverberation preprocessing. IEEE Transactions on Audio, Speech and Language Processing, 17(2), 324\u2013334.","DOI":"10.1109\/TASL.2008.2010214"},{"key":"785_CR10","doi-asserted-by":"crossref","unstructured":"Tamura, M., Masuko, T., Tokuda, K., Kobayashi, T. (2001). Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR. In Proceedings of ICASSP (Vol. 2, pp. 806\u2013808).","DOI":"10.1109\/ICASSP.2001.941037"},{"key":"785_CR11","doi-asserted-by":"crossref","unstructured":"Stolcke, A., Ferrer, L., Kajarekar, S., Shriberg, E., Venkataraman, A. (2005). MLLR transforms as features in speaker recognition. In Proceedings of Interspeech (pp. 2425\u20132428).","DOI":"10.21437\/Interspeech.2005-647"},{"issue":"2","key":"785_CR12","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1016\/j.patcog.2005.07.001","volume":"39","author":"C Sanderson","year":"2006","unstructured":"Sanderson, C., Bengio, S., Gao, Y. (2006). On transforming statistical models for non-frontal face verification. Pattern Recognition, 39(2), 288\u2013302.","journal-title":"Pattern Recognition"},{"key":"785_CR13","doi-asserted-by":"crossref","unstructured":"Maekawa, T., & Watanabe, S. (2011). Unsupervised activity recognition with user\u2019s physical characteristics data. In Proceedings of international symposium on wearable computers (ISWC 2011), (pp. 89\u201396).","DOI":"10.1109\/ISWC.2011.24"},{"key":"785_CR14","volume-title":"The HTK book (for HTK version 3.4)","author":"S Young","year":"2006","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X., Moore, G., Odell, J., Ollason, D., Povey, D. (2006). The HTK book (for HTK version 3.4). Cambridge: Cambridge University Engineering Department."},{"key":"785_CR15","doi-asserted-by":"crossref","unstructured":"Chesta, C., Siohan, O., Lee, C.-H. (1999). Maximum a posteriori linear regression for hidden Markov model adaptation. In Proceedings of Eurospeech (Vol. 1, pp. 211\u2013214).","DOI":"10.21437\/Eurospeech.1999-56"},{"issue":"5","key":"785_CR16","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1109\/TSA.2002.800555","volume":"10","author":"J-T Chien","year":"2002","unstructured":"Chien, J.-T. (2002). Quasi-Bayes linear regression for sequential learning of hidden Markov models. IEEE Transactions on Speech and Audio Processing, 10(5), 268-278","journal-title":"IEEE Transactions on Speech and Audio Processing,"},{"key":"785_CR17","doi-asserted-by":"crossref","unstructured":"Shinoda, K., & Lee, C.-H. (2001). A structural Bayes approach to speaker adaptation. IEEE Transactions on Speech and Audio Processing, 9, 276\u2013287).","DOI":"10.1109\/89.906001"},{"issue":"1","key":"785_CR18","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1006\/csla.2001.0181","volume":"16","author":"O Siohan","year":"2002","unstructured":"Siohan, O., Myrvoll, T.A., Lee, C.H. (2002). Structural maximum a posteriori linear regression for fast HMM adaptation. Computer Speech & Language, 16(1), 5\u201324.","journal-title":"Computer Speech & Language"},{"key":"785_CR19","volume-title":"Ensemble learning for hidden Markov models. Technical report, Technical report","author":"DJC MacKay","year":"1997","unstructured":"MacKay, D.J.C. (1997). Ensemble learning for hidden Markov models. Technical report, Cavendish Laboratory: University of Cambridge."},{"key":"785_CR20","doi-asserted-by":"crossref","unstructured":"Neal, R.M., & Hinton, G.E. (1998). A view of the EM algorithm that justifies incremental, sparse, and other variants. Learning in Graphical Models, 355\u2013368.","DOI":"10.1007\/978-94-011-5014-9_12"},{"issue":"2","key":"785_CR21","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1023\/A:1007665907178","volume":"37","author":"MI Jordan","year":"1999","unstructured":"Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K. (1999). An introduction to variational methods for graphical models. Machine Learning, 37(2), 183\u2013233.","journal-title":"Machine Learning"},{"key":"785_CR22","unstructured":"Attias, H. (1999). Inferring parameters structure of latent variable models by variational Bayes. In Proceedings of uncertainty in artificial intelligence (UAI) (Vol. 15, pp. 21-30)."},{"key":"785_CR23","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1016\/S0893-6080(02)00040-0","volume":"15","author":"N Ueda","year":"2002","unstructured":"Ueda, N., & Ghahramani, Z. (2002). Bayesian model search for mixture models based on optimizing variational bounds. Neural Networks, 15, 1223\u20131241.","journal-title":"Neural Networks"},{"key":"785_CR24","unstructured":"Watanabe, S., Minami, Y., Nakamura, A., Ueda, N. (2002). Application of variational Bayesian approach to speech recognition. NIPS 2002: MIT Press."},{"key":"785_CR25","doi-asserted-by":"crossref","unstructured":"Valente, F., & Wellekens, C. (2003). Variational Bayesian GMM for speech recognition. In Proceedings of Eurospeech (pp. 441\u2013444).","DOI":"10.21437\/Eurospeech.2003-165"},{"key":"785_CR26","doi-asserted-by":"crossref","unstructured":"Watanabe, S., Minami, Y., Nakamura, A., Ueda, N. (2004). Variational bayesian estimation and clustering for speech recognition. IEEE Transactions on Speech and Audio Processing, 12, 365\u2013381.","DOI":"10.1109\/TSA.2004.828640"},{"key":"785_CR27","doi-asserted-by":"crossref","unstructured":"Somervuo, P. (2004). Comparison of ML, MAP, and VB based acoustic models in large vocabulary speech recognition. In Proceedings of ICSL (Vol. 1, pp. 830\u2013833).","DOI":"10.21437\/Interspeech.2004-275"},{"key":"785_CR28","doi-asserted-by":"crossref","unstructured":"Jitsuhiro, T., & Nakamura, S. (2004). Automatic generation of non-uniform HMM structures based on variational Bayesian approach. In Proceedings of ICASSP (Vol. 1, pp. 805\u2013808).","DOI":"10.1109\/ICASSP.2004.1326108"},{"key":"785_CR29","doi-asserted-by":"crossref","unstructured":"Hashimoto, K., Zen, H., Nankaku, Y., Lee, A., Tokuda, K. (2008). Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition. In Proceedings of Interspeech.","DOI":"10.21437\/Interspeech.2008-112"},{"key":"785_CR30","unstructured":"Ogawa, A., & Takahashi, S. (2008). Weighted distance measures for efficient reduction of Gaussian mixture components in HMM-based acoustic model. In Proceedings of ICASSP (pp. 4173\u20134176)."},{"key":"785_CR31","doi-asserted-by":"crossref","unstructured":"Ding, N., & Ou, Z. (2010). Variational nonparametric Bayesian hidden Markov model. In Proceedings of ICASSP (pp. 2098\u20132101).","DOI":"10.1109\/ICASSP.2010.5495125"},{"key":"785_CR32","doi-asserted-by":"crossref","unstructured":"Watanabe, S., & Nakamura, A. (2004). Acoustic model adaptation based on coarse\/fine training of transfer vectors and its application to a speaker adaptation task. In Proceedings of ICSLP (pp. 2933\u20132936).","DOI":"10.21437\/Interspeech.2004-19"},{"key":"785_CR33","doi-asserted-by":"crossref","unstructured":"Yu, K., & Gales, M.J.F. (2006). Incremental adaptation using bayesian inference. In Proceedings of ICASSP (Vol. 1, pp. 217\u2013220).","DOI":"10.1109\/ICASSP.2006.1659996"},{"issue":"1","key":"785_CR34","first-page":"661","volume":"6","author":"J Winn","year":"2006","unstructured":"Winn, J., & Bishop, C.M. (2006). Variational message passing. Journal of Machine Learning Research, 6(1), 661.","journal-title":"Journal of Machine Learning Research"},{"key":"785_CR35","doi-asserted-by":"crossref","unstructured":"Gales, M.J.F., & Woodland, P.C. (1996). Variance compensation within the MLLR framework, Technical Report 242: Cambridge University Engineering Department.","DOI":"10.1006\/csla.1996.0013"},{"issue":"1","key":"785_CR36","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1093\/biomet\/68.1.265","volume":"68","author":"AP Dawid","year":"1981","unstructured":"Dawid, A.P. (1981). Some matrix-variate distribution theory: notational considerations and a Bayesian application. Biometrika, 68(1), 265\u2013274.","journal-title":"Biometrika"},{"key":"785_CR37","doi-asserted-by":"crossref","unstructured":"Watanabe, S., Nakamura, A., Juang, B.H. (2011). Bayesian linear regression for hidden Markov model based on optimizing variational bounds. In Proceedings of MLSP (pp. 1\u20136).","DOI":"10.1109\/MLSP.2011.6064605"},{"key":"785_CR38","unstructured":"Odell, J.J. (1995). The use of context in large vocabulary speech recognition. PhD thesis: Cambridge University."},{"key":"785_CR39","unstructured":"Maekawa, K., Koiso, H., Furui, S., Isahara, H. (2000). Spontaneous speech corpus of Japanese. In Proceedings of LREC (Vol. 2, pp. 947\u2013952)."},{"key":"785_CR40","unstructured":"Nakamura, A., Oba, T., Watanabe, S., Ishizuka, K., Fujimoto, M., Hori, T., McDermott, E., Minami, Y. (2006). Evaluation of the SOLON speech recognition system: 2006 benchmark using the corpus of spontaneous japanese. IPSJ SIG Notes, 2006(136), 251\u2013256. (in Japanese)."},{"key":"785_CR41","doi-asserted-by":"crossref","unstructured":"McDermott, E., Hazen, T.J., Le Roux, J., Nakamura, A., Katagiri, S. (2007). Discriminative training for large-vocabulary speech recognition using minimum classification error. IEEE Transactions on Audio, Speech, and Language Processing, 15(1), 203\u2013223.","DOI":"10.1109\/TASL.2006.876778"},{"key":"785_CR42","unstructured":"Hori, T. (2004). NTT speech recognizer with outlook on the next generation: SOLON. In Proceedings of NTT workshop on communication scene analysis (Vol. 1, p. SP-6.)"},{"key":"785_CR43","doi-asserted-by":"crossref","unstructured":"Hahm, S.J., Ogawa, A., Fujimoto, M., Hori, T., Nakamura, A. (2012). Speaker adaptation using variational Bayesian linear regression in normalized feature space. In Proceedings of Interspeech (pp. 803-806).","DOI":"10.21437\/Interspeech.2012-245"},{"key":"785_CR44","doi-asserted-by":"crossref","unstructured":"Hahm, S.J., Ogawa, A., Fujimoto, M., Hori, T., Nakamura, A. (2013). Feature space variational Bayesian linear regression and its combination with model space VBLR. In Proceedings of ICASSP (pp. 7898-7902).","DOI":"10.1109\/ICASSP.2013.6639202"},{"key":"785_CR45","doi-asserted-by":"crossref","unstructured":"Blei, D.M., & Jordan, M.I. (2006). Variational inference for Dirichlet process mixtures. Bayesian Analysis, 1(1), 121\u2013144.","DOI":"10.1214\/06-BA104"},{"key":"785_CR46","unstructured":"Jebara, T. (2004). Machine learning: discriminative and generative (Vol. 755). Springer."},{"key":"785_CR47","doi-asserted-by":"crossref","unstructured":"Kubo, Y., Watanabe, S., Nakamura, A., Kobayashi, T. (2010). A regularized discriminative training method of acoustic models derived by minimum relative entropy discrimination. In Proceedings of Interspeech (pp. 2954\u20132957).","DOI":"10.21437\/Interspeech.2010-27"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-013-0785-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-013-0785-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-013-0785-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,3]],"date-time":"2023-07-03T21:39:00Z","timestamp":1688420340000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-013-0785-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,16]]},"references-count":47,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,3]]}},"alternative-id":["785"],"URL":"https:\/\/doi.org\/10.1007\/s11265-013-0785-8","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8,16]]}}}