Abstract
This paper proposes a two-level Bayesian Ying-Yang (BYY) harmony learning based acoustic model discriminative training method. In this method, a rival penalized competitive learning (RPCL) simplified BYY harmony learning based discriminative training is conducted at the HMM state level to optimizing the state boundaries, while a BYY based model selection is conducted at the Gaussian mixture components level to determine the Gaussian mixture components within the same HMM state. Two levels of learning work coordinately and have good convergence. Experiments show that the trained model is more discriminative with better recognition performance, and also more compact with smaller number of Gaussian components.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Brown, P.: The acoustic-modeling problem in automatic speech recognition. Ph.D. dissertation, Carnegie Mellon University (1987)
Bahl, L., Brown, P., De Souza, P., Mercer, R.: Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In: Proc. of 1986 IEEE Intl. Conf. on ICASSP, pp. 49–52 (1986)
Juang, B.H., Katagiri, S.: Discriminative learning for minimum error classification. IEEE Trans. on Signal Processing 40(12), 3043–3054 (1992)
Povey, D., Woodland, P.C.: Minimum phone error and I-smothing for improved discriminative training. In: Proc. of 2002 IEEE Intl. Conf. on ICASSP, pp. 105–108 (2002)
Pang, Z.H., Wu, X.H., Xu, L.: A Comparative Study of RPCL and MCE Based Discriminative Training Methods for LVCSR. In: Zhang, Y., Zhou, Z.-H., Zhang, C., Li, Y. (eds.) IScIDE 2011. LNCS, vol. 7202, pp. 27–34. Springer, Heidelberg (2012)
Pang, Z.H., Tu, S.K., Su, D., Wu, X.H., Xu, L.: Discriminative training of GMM-HMM acoustic model by RPCL learning. Frontiers of Electrical and Electronic Engineering in China 6(2), 283–290 (2011)
Xu, L.: Bayesian-kullback coupled ying-yang machines: unified learning and new results on vector quantization. In: Proc. Intl. Conf. on Neural Information Processing, pp. 977–988 (1995)
Su, D., Wu, X.H., Xu, L.: GMM-HMM acoustic model training by a two level procedure with Gaussian components determined by automatic model selection. In: Proc. of 2010 IEEE Intl. Conf. on ICASSP, pp. 4890–4893 (2010)
Xu, L.: Rival penalized competitive learning. Scholarpedia 2(8), 1810 (2007)
Xu, L.: Bayesian Ying-Yang system, best harmony learning, and five action circling. Frontiers of Electrical and Electronic Engineering in China 5(3), 281–328 (2010)
Xu, L.: On essential topics of BYY harmony learning: Current status, challenging issues, and gene analysis applications. Frontiers of Electrical and Electronic Engineering in China 7(1), 147–196 (2012)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pang, Z., Tu, S., Wu, X., Xu, L. (2013). Discriminative GMM-HMM Acoustic Model Selection Using Two-Level Bayesian Ying-Yang Harmony Learning. In: Yang, J., Fang, F., Sun, C. (eds) Intelligent Science and Intelligent Data Engineering. IScIDE 2012. Lecture Notes in Computer Science, vol 7751. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36669-7_87
Download citation
DOI: https://doi.org/10.1007/978-3-642-36669-7_87
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36668-0
Online ISBN: 978-3-642-36669-7
eBook Packages: Computer ScienceComputer Science (R0)