IEICE TRANSACTIONS on Information
A Hybrid HMM/BN Acoustic Model for Automatic Speech Recognition
Summary :
In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorithms has limited their application in continuous speech recognition. In this paper we propose new acoustic model, where HMM are used for modeling of temporal speech characteristics and state probability model is represented by BN. In our experimental system based on HMM/BN model, in addition to speech observation variable, state BN has two more (hidden) variables representing noise type and SNR value. Evaluation results on AURORA2 database showed 36.4% word error rate reduction for closed noise test which is comparable with other much more complex systems utilizing effective adaptation and noise robust methods.
- Publication
- IEICE TRANSACTIONS on Information Vol.E86-D No.3 pp.438-445
- Publication Date
- 2003/03/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Issue on Speech Information Processing)
- Category
- Speech and Speaker Recognition
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
Konstantin MARKOV, Satoshi NAKAMURA, "A Hybrid HMM/BN Acoustic Model for Automatic Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E86-D, no. 3, pp. 438-445, March 2003, doi: .
Abstract: In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorithms has limited their application in continuous speech recognition. In this paper we propose new acoustic model, where HMM are used for modeling of temporal speech characteristics and state probability model is represented by BN. In our experimental system based on HMM/BN model, in addition to speech observation variable, state BN has two more (hidden) variables representing noise type and SNR value. Evaluation results on AURORA2 database showed 36.4% word error rate reduction for closed noise test which is comparable with other much more complex systems utilizing effective adaptation and noise robust methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/e86-d_3_438/_p
Copy
@ARTICLE{e86-d_3_438,
author={Konstantin MARKOV, Satoshi NAKAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={A Hybrid HMM/BN Acoustic Model for Automatic Speech Recognition},
year={2003},
volume={E86-D},
number={3},
pages={438-445},
abstract={In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorithms has limited their application in continuous speech recognition. In this paper we propose new acoustic model, where HMM are used for modeling of temporal speech characteristics and state probability model is represented by BN. In our experimental system based on HMM/BN model, in addition to speech observation variable, state BN has two more (hidden) variables representing noise type and SNR value. Evaluation results on AURORA2 database showed 36.4% word error rate reduction for closed noise test which is comparable with other much more complex systems utilizing effective adaptation and noise robust methods.},
keywords={},
doi={},
ISSN={},
month={March},}
Copy
TY - JOUR
TI - A Hybrid HMM/BN Acoustic Model for Automatic Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 438
EP - 445
AU - Konstantin MARKOV
AU - Satoshi NAKAMURA
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E86-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2003
AB - In current HMM based speech recognition systems, it is difficult to supplement acoustic spectrum features with additional information such as pitch, gender, articulator positions, etc. On the other hand, Bayesian Networks (BN) allow for easy combination of different continuous as well as discrete features by exploring conditional dependencies between them. However, the lack of efficient algorithms has limited their application in continuous speech recognition. In this paper we propose new acoustic model, where HMM are used for modeling of temporal speech characteristics and state probability model is represented by BN. In our experimental system based on HMM/BN model, in addition to speech observation variable, state BN has two more (hidden) variables representing noise type and SNR value. Evaluation results on AURORA2 database showed 36.4% word error rate reduction for closed noise test which is comparable with other much more complex systems utilizing effective adaptation and noise robust methods.
ER -
English
