乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T21:10:26Z","timestamp":1687900226159},"reference-count":37,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[2013,3,1]],"date-time":"2013-03-01T00:00:00Z","timestamp":1362096000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2013,3]]},"DOI":"10.1016\/j.specom.2012.12.002","type":"journal-article","created":{"date-parts":[[2012,12,14]],"date-time":"2012-12-14T16:15:18Z","timestamp":1355501718000},"page":"415-431","source":"Crossref","is-referenced-by-count":1,"title":["Prior-shared feature and model space speaker adaptation by consistently employing map estimation"],"prefix":"10.1016","volume":"55","author":[{"given":"Seong-Jun","family":"Hahm","sequence":"first","affiliation":[]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[]},{"given":"Masakiyo","family":"Fujimoto","sequence":"additional","affiliation":[]},{"given":"Takaaki","family":"Hori","sequence":"additional","affiliation":[]},{"given":"Atsushi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.specom.2012.12.002_b0005","unstructured":"Anastasakos, T., McDonough, J., Makhoul, J., 1997. Speaker adaptive training: a maximum likelihood approach to speaker normalization. In: Proc. of ICASSP, vol. 2, pp. 1043\u20131046."},{"issue":"2","key":"10.1016\/j.specom.2012.12.002_b0010","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1109\/TPAMI.1983.4767370","article-title":"A maximum likelihood approach to continuous speech recognition","volume":"5","author":"Bahl","year":"1983","journal-title":"IEEE Trans. Pattern Anal Machine Intell."},{"key":"10.1016\/j.specom.2012.12.002_b0015","doi-asserted-by":"crossref","unstructured":"Breslin, C., Chin, K., Gales, M., Knill, K., Xu, H., 2010. Prior information for rapid speaker adaptation. In: Proc. of INTERSPEECH, pp. 1644\u20131647.","DOI":"10.21437\/Interspeech.2010-475"},{"key":"10.1016\/j.specom.2012.12.002_b0020","doi-asserted-by":"crossref","unstructured":"Chen, K., Liau, W., Wang, H., Lee, L., 2000. Fast speaker adaptation using eigenspace-based maximum likelihood linear regression. In: Proc. of INTERSPEECH, pp. 742\u2013745.","DOI":"10.21437\/ICSLP.2000-642"},{"key":"10.1016\/j.specom.2012.12.002_b0025","doi-asserted-by":"crossref","unstructured":"Chou, W., 1999. Maximum a posterior linear regression with elliptically symmetric matrix variate priors. In: Proc. of EUROSPEECH, pp. 1\u20134.","DOI":"10.21437\/Eurospeech.1999-4"},{"issue":"5","key":"10.1016\/j.specom.2012.12.002_b0030","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/89.466659","article-title":"Speaker adaptation using constrained estimation of Gaussian mixtures","volume":"3","author":"Digalakis","year":"1995","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.specom.2012.12.002_b0035","unstructured":"Eide, E., Gish, H., 1996. A parametric approach to vocal tract length normalization. In: Proc. of ICASSP, vol. 1, pp. 346\u2013348."},{"key":"10.1016\/j.specom.2012.12.002_b0040","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1006\/csla.1998.0043","article-title":"Maximum likelihood linear transformations for HMM-based speech recognition","volume":"12","author":"Gales","year":"1998","journal-title":"Comput. Speech Lang."},{"issue":"2","key":"10.1016\/j.specom.2012.12.002_b0045","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/89.279278","article-title":"Maximum a posteriori estimation for multivariate Gaussian mixture observation of Markov chains","volume":"2","author":"Gauvain","year":"1994","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.specom.2012.12.002_b0050","doi-asserted-by":"crossref","unstructured":"Glass, J., Hazen, T., Cyphers, S., Malioutov, I., Huynh, D., Barzilay, R., 2007. Recent progress in the MIT spoken lecture processing project. In: Proc. of INTERSPEECH, pp. 2553\u20132556.","DOI":"10.21437\/Interspeech.2007-678"},{"key":"10.1016\/j.specom.2012.12.002_b0055","doi-asserted-by":"crossref","unstructured":"Hahm, S., Ohkawa, Y., Ito, M., Suzuki, M., Ito, A., Makino, S., 2010a. Aspect-model-based reference speaker weighting. In: Proc. of ICASSP, pp. 4302\u20134305.","DOI":"10.1109\/ICASSP.2010.5495672"},{"issue":"7","key":"10.1016\/j.specom.2012.12.002_b0060","doi-asserted-by":"crossref","first-page":"1927","DOI":"10.1587\/transinf.E93.D.1927","article-title":"Improved reference speaker weighting using aspect model","volume":"93","author":"Hahm","year":"2010","journal-title":"IEICE Trans. Inf. Systems"},{"issue":"1","key":"10.1016\/j.specom.2012.12.002_b0065","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/S0167-6393(99)00059-X","article-title":"A comparison of novel techniques for rapid speaker adaptation","volume":"31","author":"Hazen","year":"2000","journal-title":"Speech Comm."},{"issue":"4","key":"10.1016\/j.specom.2012.12.002_b0070","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1109\/TASL.2006.889790","article-title":"Efficient WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition","volume":"15","author":"Hori","year":"2007","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2012.12.002_b0075","unstructured":"Huang, J., Marcheret, E., Visweswariah, K., 2005. Rapid feature space speaker adaptation for multi-stream HMM-based audio-visual speech recognition. In: Proc. of IEEE Internat. Conf. on Multimedia and Expo (ICME), pp. 338\u2013341."},{"issue":"6","key":"10.1016\/j.specom.2012.12.002_b0080","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1109\/89.876308","article-title":"Rapid speaker adaptation in eigenvoice space","volume":"8","author":"Kuhn","year":"2000","journal-title":"IEEE Trans. Speech Audio Process. (SAP)"},{"issue":"4","key":"10.1016\/j.specom.2012.12.002_b0085","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1109\/78.80902","article-title":"A study on speaker adaptation of the parameters of continuous density hidden Markov models","volume":"39","author":"Lee","year":"1991","journal-title":"IEEE Trans. Signal Process."},{"issue":"2","key":"10.1016\/j.specom.2012.12.002_b0090","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","article-title":"Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models","volume":"9","author":"Leggetter","year":"1995","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2012.12.002_b0095","doi-asserted-by":"crossref","unstructured":"Lei, X., Hamaker, J., He, X., 2006. Robust feature space adaptation for telephony speech recognition. In: Proc. of INTERSPEECH, pp. 773\u2013776.","DOI":"10.21437\/Interspeech.2006-268"},{"key":"10.1016\/j.specom.2012.12.002_b0100","unstructured":"Maekawa, K., Koiso, H., Furui, S., Isahara, H., 2000. Spontaneous speech corpus of Japanese. In: Proc. of LREC2000, vol. 2, pp. 947\u2013952."},{"issue":"2","key":"10.1016\/j.specom.2012.12.002_b0105","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1093\/biomet\/80.2.267","article-title":"Maximum likelihood estimation via the ECM algorithm: a general framework","volume":"80","author":"Meng","year":"1993","journal-title":"Biometrika"},{"key":"10.1016\/j.specom.2012.12.002_b0110","unstructured":"Moreno, P., Raj, B., Stern, R., 1996. A vector Taylor series approach for environment-independent speech recognition. In: Proc. of ICASSP, pp. 733\u2013736."},{"key":"10.1016\/j.specom.2012.12.002_b0115","doi-asserted-by":"crossref","unstructured":"Nakano, Y., Tachibana, M., Yamagishi, J., Kobayashi, T., 2006. Constrained structural maximum a posteriori linear regression for average-voice-based speech synthesis. In: Proc. of INTERSPEECH, pp. 2286\u20132289.","DOI":"10.21437\/Interspeech.2006-587"},{"key":"10.1016\/j.specom.2012.12.002_b0120","doi-asserted-by":"crossref","unstructured":"Povey, D., Saon, G., 2006. Feature and model space speaker adaptation with full covariance Gaussians. In: Proc. of INTERSPEECH, pp. 1145\u20131148.","DOI":"10.21437\/Interspeech.2006-349"},{"key":"10.1016\/j.specom.2012.12.002_b0125","unstructured":"Pye, D., Woodland, P.C., 1997. Experiments in speaker normalisation and adaptation for large vocabulary speech recognition. In: Proc. of ICASSP, vol. 2, pp. 1047\u20131050."},{"key":"10.1016\/j.specom.2012.12.002_b0130","series-title":"Fundamentals of Speech Recognition","author":"Rabiner","year":"1993"},{"issue":"3","key":"10.1016\/j.specom.2012.12.002_b0135","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1109\/89.906001","article-title":"A structural Bayes approach to speaker adaptation","volume":"9","author":"Shinoda","year":"2001","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"4","key":"10.1016\/j.specom.2012.12.002_b0140","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/89.917687","article-title":"Joint maximum a posteriori adaptation of transformation and HMM parameters","volume":"9","author":"Siohan","year":"2001","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1","key":"10.1016\/j.specom.2012.12.002_b0145","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1006\/csla.2001.0181","article-title":"Structural maximum a posteriori linear regression for fast HMM adaptation","volume":"16","author":"Siohan","year":"2002","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.specom.2012.12.002_b0150","series-title":"Introduction to Linear Algebra","author":"Strang","year":"2003"},{"issue":"4","key":"10.1016\/j.specom.2012.12.002_b0155","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1109\/TSA.2004.828640","article-title":"Variational Bayesian estimation and clustering for speech recognition","volume":"12","author":"Watanabe","year":"2004","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"2","key":"10.1016\/j.specom.2012.12.002_b0160","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1109\/TASL.2009.2029717","article-title":"Predictor\u2013corrector adaptation by using time evolution system with macroscopic time scale","volume":"18","author":"Watanabe","year":"2010","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2012.12.002_b0165","doi-asserted-by":"crossref","unstructured":"Watanabe, S., Nakamura, A., Juang, B., 2011. Bayesian linear regression for Hidden Markov Model based on optimizing variational bounds. In: IEEE Internat. Workshop on Machine Learning for Signal Processing (MLSP), pp. 1\u20136.","DOI":"10.1109\/MLSP.2011.6064605"},{"key":"10.1016\/j.specom.2012.12.002_b0170","unstructured":"Woodland, P.C., 2001. Speaker adaptation for continuous density HMMs: a review. In: ISCA Tutorial and Research Workshop (ITRW) on Adaptation Methods for Speech Recognition."},{"key":"10.1016\/j.specom.2012.12.002_b0175","unstructured":"Yu, K., Gales, M., 2006. Incremental adaptation using Bayesian inference. In: IEEE Internat. Conf. on Acoustics, Speech and Signal Processing, ICASSP 2006 Proceedings, vol. 1, pp. 217\u2013220."},{"issue":"6","key":"10.1016\/j.specom.2012.12.002_b0180","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.1109\/TASL.2007.901300","article-title":"Bayesian adaptive inference and adaptive training","volume":"15","author":"Yu","year":"2007","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.specom.2012.12.002_b0185","doi-asserted-by":"crossref","unstructured":"Zaj\u00edc, Z., Machlica, L., M\u00fcller, L., 2009. Refinement approach for adaptation based on combination of MAP and fMLLR. In: Proc. of the 12th Internat. Conf. on Text, Speech and Dialogue, pp. 274\u2013281.","DOI":"10.1007\/978-3-642-04208-9_39"}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639312001409?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639312001409?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T20:37:30Z","timestamp":1687898250000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639312001409"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,3]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,3]]}},"alternative-id":["S0167639312001409"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2012.12.002","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2013,3]]}}}