Bayesian Context Clustering Using Cross Validation for Speech Recognition
Summary :
This paper proposes Bayesian context clustering using cross validation for hidden Markov model (HMM) based speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by treating model parameters as random variables. The variational Bayesian method, which is widely used as an efficient approximation of the Bayesian approach, has been applied to HMM-based speech recognition, and it shows good performance. Moreover, the Bayesian approach can select an appropriate model structure while taking account of the amount of training data. Since prior distributions which represent prior information about model parameters affect estimation of the posterior distributions and selection of model structure (e.g., decision tree based context clustering), the determination of prior distributions is an important problem. However, it has not been thoroughly investigated in speech recognition, and the determination technique of prior distributions has not performed well. The proposed method can determine reliable prior distributions without any tuning parameters and select an appropriate model structure while taking account of the amount of training data. Continuous phoneme recognition experiments show that the proposed method achieved a higher performance than the conventional methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E94-D No.3 pp.668-678
- Publication Date
- 2011/03/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E94.D.668
- Type of Manuscript
- PAPER
- Category
- Speech and Hearing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kei HASHIMOTO, Heiga ZEN, Yoshihiko NANKAKU, Akinobu LEE, Keiichi TOKUDA, "Bayesian Context Clustering Using Cross Validation for Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 3, pp. 668-678, March 2011, doi: 10.1587/transinf.E94.D.668.
Abstract: This paper proposes Bayesian context clustering using cross validation for hidden Markov model (HMM) based speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by treating model parameters as random variables. The variational Bayesian method, which is widely used as an efficient approximation of the Bayesian approach, has been applied to HMM-based speech recognition, and it shows good performance. Moreover, the Bayesian approach can select an appropriate model structure while taking account of the amount of training data. Since prior distributions which represent prior information about model parameters affect estimation of the posterior distributions and selection of model structure (e.g., decision tree based context clustering), the determination of prior distributions is an important problem. However, it has not been thoroughly investigated in speech recognition, and the determination technique of prior distributions has not performed well. The proposed method can determine reliable prior distributions without any tuning parameters and select an appropriate model structure while taking account of the amount of training data. Continuous phoneme recognition experiments show that the proposed method achieved a higher performance than the conventional methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.668/_p
Copy
@ARTICLE{e94-d_3_668,
author={Kei HASHIMOTO, Heiga ZEN, Yoshihiko NANKAKU, Akinobu LEE, Keiichi TOKUDA, },
journal={IEICE TRANSACTIONS on Information},
title={Bayesian Context Clustering Using Cross Validation for Speech Recognition},
year={2011},
volume={E94-D},
number={3},
pages={668-678},
abstract={This paper proposes Bayesian context clustering using cross validation for hidden Markov model (HMM) based speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by treating model parameters as random variables. The variational Bayesian method, which is widely used as an efficient approximation of the Bayesian approach, has been applied to HMM-based speech recognition, and it shows good performance. Moreover, the Bayesian approach can select an appropriate model structure while taking account of the amount of training data. Since prior distributions which represent prior information about model parameters affect estimation of the posterior distributions and selection of model structure (e.g., decision tree based context clustering), the determination of prior distributions is an important problem. However, it has not been thoroughly investigated in speech recognition, and the determination technique of prior distributions has not performed well. The proposed method can determine reliable prior distributions without any tuning parameters and select an appropriate model structure while taking account of the amount of training data. Continuous phoneme recognition experiments show that the proposed method achieved a higher performance than the conventional methods.},
keywords={},
doi={10.1587/transinf.E94.D.668},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Bayesian Context Clustering Using Cross Validation for Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 668
EP - 678
AU - Kei HASHIMOTO
AU - Heiga ZEN
AU - Yoshihiko NANKAKU
AU - Akinobu LEE
AU - Keiichi TOKUDA
PY - 2011
DO - 10.1587/transinf.E94.D.668
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2011
AB - This paper proposes Bayesian context clustering using cross validation for hidden Markov model (HMM) based speech recognition. The Bayesian approach is a statistical technique for estimating reliable predictive distributions by treating model parameters as random variables. The variational Bayesian method, which is widely used as an efficient approximation of the Bayesian approach, has been applied to HMM-based speech recognition, and it shows good performance. Moreover, the Bayesian approach can select an appropriate model structure while taking account of the amount of training data. Since prior distributions which represent prior information about model parameters affect estimation of the posterior distributions and selection of model structure (e.g., decision tree based context clustering), the determination of prior distributions is an important problem. However, it has not been thoroughly investigated in speech recognition, and the determination technique of prior distributions has not performed well. The proposed method can determine reliable prior distributions without any tuning parameters and select an appropriate model structure while taking account of the amount of training data. Continuous phoneme recognition experiments show that the proposed method achieved a higher performance than the conventional methods.
ER -
English
