Copy

Sakriani SAKTI, Satoshi NAKAMURA, Konstantin MARKOV, "Improving Acoustic Model Precision by Incorporating a Wide Phonetic Context Based on a Bayesian Framework" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 3, pp. 946-953, March 2006, doi:10.1093/ietisy/e89-d.3.946.
Abstract:Over the last decade, the Bayesian approach has increased in popularity in many application areas. It uses a probabilistic framework which encodes our beliefs or actions in situations of uncertainty. Information from several models can also be combined based on the Bayesian framework to achieve better inference and to better account for modeling uncertainty. The approach we adopted here is to utilize the benefits of the Bayesian framework to improve acoustic model precision in speech recognition systems, which modeling a wider-than-triphone context by approximating it using several less context-dependent models. Such a composition was developed in order to avoid the crucial problem of limited training data and to reduce the model complexity. To enhance the model reliability due to unseen contexts and limited training data, flooring and smoothing techniques are applied. Experimental results show that the proposed Bayesian pentaphone model improves word accuracy in comparison with the standard triphone model.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.3.946/_p

Copy

@ARTICLE{e89-d_3_946,
author={Sakriani SAKTI, Satoshi NAKAMURA, Konstantin MARKOV, },
journal={IEICE TRANSACTIONS on Information},
title={Improving Acoustic Model Precision by Incorporating a Wide Phonetic Context Based on a Bayesian Framework},
year={2006},
volume={E89-D},
number={3},
pages={946-953},
abstract={Over the last decade, the Bayesian approach has increased in popularity in many application areas. It uses a probabilistic framework which encodes our beliefs or actions in situations of uncertainty. Information from several models can also be combined based on the Bayesian framework to achieve better inference and to better account for modeling uncertainty. The approach we adopted here is to utilize the benefits of the Bayesian framework to improve acoustic model precision in speech recognition systems, which modeling a wider-than-triphone context by approximating it using several less context-dependent models. Such a composition was developed in order to avoid the crucial problem of limited training data and to reduce the model complexity. To enhance the model reliability due to unseen contexts and limited training data, flooring and smoothing techniques are applied. Experimental results show that the proposed Bayesian pentaphone model improves word accuracy in comparison with the standard triphone model.},
keywords={},
doi={10.1093/ietisy/e89-d.3.946},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Improving Acoustic Model Precision by Incorporating a Wide Phonetic Context Based on a Bayesian Framework
T2 - IEICE TRANSACTIONS on Information
SP - 946
EP - 953
AU - Sakriani SAKTI
AU - Satoshi NAKAMURA
AU - Konstantin MARKOV
PY - 2006
DO -10.1093/ietisy/e89-d.3.946
JO - IEICE TRANSACTIONS on Information
SN -1745-1361
VL - E89-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2006
AB -Over the last decade, the Bayesian approach has increased in popularity in many application areas. It uses a probabilistic framework which encodes our beliefs or actions in situations of uncertainty. Information from several models can also be combined based on the Bayesian framework to achieve better inference and to better account for modeling uncertainty. The approach we adopted here is to utilize the benefits of the Bayesian framework to improve acoustic model precision in speech recognition systems, which modeling a wider-than-triphone context by approximating it using several less context-dependent models. Such a composition was developed in order to avoid the crucial problem of limited training data and to reduce the model complexity. To enhance the model reliability due to unseen contexts and limited training data, flooring and smoothing techniques are applied. Experimental results show that the proposed Bayesian pentaphone model improves word accuracy in comparison with the standard triphone model.
ER -