{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:47:26Z","timestamp":1760708846847,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,6,10]],"date-time":"2015-06-10T00:00:00Z","timestamp":1433894400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["61273264"],"award-info":[{"award-number":["61273264"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The electronic information industry development fund of China","award":["2013-472"],"award-info":[{"award-number":["2013-472"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s11265-015-1012-6","type":"journal-article","created":{"date-parts":[[2015,6,10]],"date-time":"2015-06-10T15:25:27Z","timestamp":1433949927000},"page":"175-185","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Speaker Adaptation of Hybrid NN\/HMM Model for Speech Recognition Based on Singular Value Decomposition"],"prefix":"10.1007","volume":"82","author":[{"given":"Shaofei","family":"Xue","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lirong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingfeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,6,10]]},"reference":[{"key":"1012_CR1","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"JL Gauvain","year":"1994","unstructured":"Gauvain, J.L., & Lee, C.-H. (1994). Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Transactions on Speech and Audio Processing, 2, 291\u2013298.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"1012_CR2","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1006\/csla.1997.0031","volume":"11","author":"SM Ahadi","year":"1997","unstructured":"Ahadi, S.M., & Woodland, P.C. (1997). Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models. Computer Speech & Language, 11, 187\u2013206.","journal-title":"Computer Speech & Language"},{"key":"1012_CR3","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1006\/csla.1995.0010","volume":"9","author":"C Leggetter","year":"1995","unstructured":"Leggetter, C., & Woodland, P.C. (1995). Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech & Language, 9, 171\u2013185.","journal-title":"Computer Speech & Language"},{"key":"1012_CR4","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJF Gales","year":"1998","unstructured":"Gales, M.J.F. (1998). Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech & Language, 12, 75\u201398.","journal-title":"Computer Speech & Language"},{"key":"1012_CR5","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1109\/89.466659","volume":"3","author":"VV Digalakis","year":"1995","unstructured":"Digalakis, V.V., Rtischev, D., & Neumeyer, L.G. (1995). Speaker adaptation using constrained estimation of Gaussian mixtures. IEEE Transactions on Speech and Audio Processing, 3, 357\u2013Lb366.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"1012_CR6","first-page":"353","volume":"1","author":"L Lee","year":"1996","unstructured":"Lee, L., & Rose, R.C. (1996). Speaker normalization using efficient frequency warping procedures. IEEE International Conference of Acoustics Speech and Signal Processing (ICASSP), 1, 353\u2013356.","journal-title":"IEEE International Conference of Acoustics Speech and Signal Processing (ICASSP)"},{"key":"1012_CR7","first-page":"217","volume":"1","author":"H Jiang","year":"2001","unstructured":"Jiang, H., Soong, F., & Lee, C.-H. (2001). Hierarchical stochastic feature matching for robust speech recognition. IEEE International Conference of Acoustics Speech and Signal Processing (ICASSP), 1, 217\u2013220.","journal-title":"IEEE International Conference of Acoustics Speech and Signal Processing (ICASSP)"},{"doi-asserted-by":"crossref","unstructured":"Neto, J., Almeida, L., Hochberg, M., Martins, C., Nunes, L., Renals, S., & Robinson, T. (1995). Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system, EUROSPEECH.","key":"1012_CR8","DOI":"10.21437\/Eurospeech.1995-411"},{"key":"1012_CR9","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1016\/j.specom.2006.11.005","volume":"49","author":"R Gemello","year":"2007","unstructured":"Gemello, R., Mana, F., Scanzio, S., Laface, P., & De Mori, R. (2007). Linear hidden transformations for adaptation of hybrid ANN\/HMM models. Speech Communication, 49, 827\u2013835.","journal-title":"Speech Communication"},{"doi-asserted-by":"crossref","unstructured":"Li, B., & Sim, K.C. (2010). Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN\/HMM systems.","key":"1012_CR10","DOI":"10.21437\/Interspeech.2010-214"},{"doi-asserted-by":"crossref","unstructured":"Stadermann, J., & Rigoll, G. (2005). Two-stage speaker adaptation of hybrid tied-posterior acoustic models. In IEEE international conference of acoustics, speech and signal processing (ICASSP).","key":"1012_CR11","DOI":"10.1109\/ICASSP.2005.1415279"},{"key":"1012_CR12","doi-asserted-by":"crossref","first-page":"2152","DOI":"10.1109\/TASL.2013.2270370","volume":"21","author":"SM Siniscalchi","year":"2013","unstructured":"Siniscalchi, S.M., Li, J., & Lee, C.-H. (2013). Hermitian polynomial for speaker adaptation of connectionist speech recognition systems. IEEE Transactions on Audio Speech, and Language Processing, 21, 2152\u20132161.","journal-title":"IEEE Transactions on Audio Speech, and Language Processing"},{"doi-asserted-by":"crossref","unstructured":"Seide, F., Li, G., Chen, X., & Yu, D. (2011). Feature engineering in context-dependent deep neural networks for conversational speech transcription. In 2011 IEEE workshop on automatic speech recognition and understanding (ASRU).","key":"1012_CR13","DOI":"10.1109\/ASRU.2011.6163899"},{"doi-asserted-by":"crossref","unstructured":"Yao, K., Yu, D., Seide, F., Su, H., Deng, L., & Gong, Y. (2012). Adaptation of context-dependent deep neural networks for automatic speech recognition, spoken language technology workshop (SLT).","key":"1012_CR14","DOI":"10.1109\/SLT.2012.6424251"},{"doi-asserted-by":"crossref","unstructured":"Yu, D., Yao, K., Su, H., Li, G., & Seide, F. (2013). KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition. In IEEE international conference of acoustics, speech and signal processing (ICASSP) (pp. 7893\u20137897).","key":"1012_CR15","DOI":"10.1109\/ICASSP.2013.6639201"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y.Q, & Gales, M.J.F. (2013). Tandem system adaptation using multiple linear feature transforms. In IEEE international conference of acoustics, speech and signal processing (ICASSP) (pp. 7932\u20137936).","key":"1012_CR16","DOI":"10.1109\/ICASSP.2013.6639209"},{"doi-asserted-by":"crossref","unstructured":"Tuske, Z., Schluter, R., & Ney, H. (2013). Deep hierarchical bottleneck MRASTA features for LVCSR. In IEEE international conference of acoustics, speech and signal processing (ICASSP) (pp. 6970\u20136974).","key":"1012_CR17","DOI":"10.1109\/ICASSP.2013.6639013"},{"doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., & Jiang, H. (2013). Fast speaker adaptation of hybrid NN\/HMM model for speech recognition based on discriminative learning of speaker code. In IEEE international conference of acoustics, speech and signal processing (ICASSP) (pp. 7942\u20137946).","key":"1012_CR18","DOI":"10.1109\/ICASSP.2013.6639211"},{"doi-asserted-by":"crossref","unstructured":"Abdel-Hamid, O., & Jiang, H. (2013). Rapid and effective speaker adaptation of convolutional neural network based models for speech recognition, INTERSPEECH.","key":"1012_CR19","DOI":"10.21437\/Interspeech.2013-336"},{"doi-asserted-by":"crossref","unstructured":"Xue, S., Abdel-Hamid, O.s, Jiang, H., & Dai, L. (2014). Direct adaptation of hybrid DNN\/HMM model for fast speaker adaptation in LVCSR based on speaker code. In IEEE international conference of acoustics, speech and signal processing (ICASSP).","key":"1012_CR20","DOI":"10.1109\/ICASSP.2014.6854824"},{"unstructured":"Xue, S., Abdel-Hamid, O., Jiang, H., & Dai, L. (2014). Speaker adaptation of deep neural network based on discriminant codes. In IEEE\/ACM transactions on acoustics, speech and signal processing (p. 22).","key":"1012_CR21"},{"doi-asserted-by":"crossref","unstructured":"Xue, J., Li, J., Yu, D., Seltzer, M., & Gong, Y. (2014). Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network. In IEEE international conference of acoustics, speech and signal processing (ICASSP).","key":"1012_CR22","DOI":"10.1109\/ICASSP.2014.6854828"},{"doi-asserted-by":"crossref","unstructured":"Vesely\u0300, K., Ghoshal, A., Burget, L., & Povey, D. (2013). Sequence-discriminative training of deep neural networks, INTERSPEECH.","key":"1012_CR23","DOI":"10.21437\/Interspeech.2013-548"},{"unstructured":"Denil, M., Shakibi, B., Dinh, L., de Freitas, N., et al. (2013). Predicting parameters in deep learning, advances in neural information processing systems.","key":"1012_CR24"},{"doi-asserted-by":"crossref","unstructured":"Sainath, T.N., Kingsbury, B., Sindhwani, V., Arisoy, E., & Ramabhadran, B. (2013). Low-rank matrix factorization for deep neural network training with high-dimensional output targets. In IEEE international conference of acoustics, speech and signal processing (ICASSP) (pp. 6655\u20136659).","key":"1012_CR25","DOI":"10.1109\/ICASSP.2013.6638949"},{"doi-asserted-by":"crossref","unstructured":"Xue, J., Li, J., & Gongm, Y. (2013). Restructuring of deep neural network acoustic models with singular value decomposition, INTERSPEECH.","key":"1012_CR26","DOI":"10.21437\/Interspeech.2013-552"},{"key":"1012_CR27","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/29.46546","volume":"37","author":"K-F Lee","year":"1989","unstructured":"Lee, K.-F., & Hon, H.-W. (1989). Speaker-independent phone recognition using hidden Markov models. IEEE Transactions on Acoustics, Speech and Signal Processing, 37, 1641\u20131648.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"doi-asserted-by":"crossref","unstructured":"Pan, J., Liu, C., Wang, Z., Hu, Y., & Jiang, H. (2012). Investigation of deep neural networks (DNN) for large vocabulary continuous speech recognition: Why DNN surpasses GMMs in acoustic modeling. In 8th international symposium on chinese spoken language processing (ISCSLP) (pp. 301\u2013305).","key":"1012_CR28","DOI":"10.1109\/ISCSLP.2012.6423452"},{"key":"1012_CR29","first-page":"562","volume":"1","author":"Y Bao","year":"2012","unstructured":"Bao, Y., Jiang, H., Liu, C., Hu, Y., & Dai, L. (2012). Investigation on dimensionality reduction of concatenated features with deep neural network for LVCSR systems. IEEE 11th International Conference on Signal Processing (ICSP), 1, 562\u2013566.","journal-title":"IEEE 11th International Conference on Signal Processing (ICSP)"},{"doi-asserted-by":"crossref","unstructured":"Bao, Y., Jiang, H., Dai, L., & Liu, C. (2013). Incoherent training of deep neural networks to de-correlate bottleneck features for speech recognition. In IEEE international conference of acoustics, speech and signal processing (ICASSP).","key":"1012_CR30","DOI":"10.1109\/ICASSP.2013.6639015"},{"doi-asserted-by":"crossref","unstructured":"Zhang, S., Bao, Y., Zhou, P., Jiang, H., & Dai, L. (2014). Improving deep neural networks for LVCSR using dropout and shrinking structure. In IEEE international conference of acoustics, speech and signal processing (ICASSP).","key":"1012_CR31","DOI":"10.1109\/ICASSP.2014.6854927"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1012-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-015-1012-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-015-1012-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T07:18:10Z","timestamp":1691738290000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-015-1012-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6,10]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["1012"],"URL":"https:\/\/doi.org\/10.1007\/s11265-015-1012-6","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"type":"print","value":"1939-8018"},{"type":"electronic","value":"1939-8115"}],"subject":[],"published":{"date-parts":[[2015,6,10]]}}}