Outlier Detection and Removal for HMM-Based Speech Synthesis with an Insufficient Speech Database
Summary :
Decision tree-based clustering and parameter estimation are essential steps in the training part of an HMM-based speech synthesis system. These two steps are usually performed based on the maximum likelihood (ML) criterion. However, one of the drawbacks of the ML criterion is that it is sensitive to outliers which usually result in quality degradation of the synthesized speech. In this letter, we propose an approach to detect and remove outliers for HMM-based speech synthesis. Experimental results show that the proposed approach can improve the synthetic speech, particularly when the available training speech database is insufficient.
- Publication
- IEICE TRANSACTIONS on Information Vol.E95-D No.9 pp.2351-2354
- Publication Date
- 2012/09/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E95.D.2351
- Type of Manuscript
- LETTER
- 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
Doo Hwa HONG, June Sig SUNG, Kyung Hwan OH, Nam Soo KIM, "Outlier Detection and Removal for HMM-Based Speech Synthesis with an Insufficient Speech Database" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 9, pp. 2351-2354, September 2012, doi: 10.1587/transinf.E95.D.2351.
Abstract: Decision tree-based clustering and parameter estimation are essential steps in the training part of an HMM-based speech synthesis system. These two steps are usually performed based on the maximum likelihood (ML) criterion. However, one of the drawbacks of the ML criterion is that it is sensitive to outliers which usually result in quality degradation of the synthesized speech. In this letter, we propose an approach to detect and remove outliers for HMM-based speech synthesis. Experimental results show that the proposed approach can improve the synthetic speech, particularly when the available training speech database is insufficient.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.2351/_p
Copy
@ARTICLE{e95-d_9_2351,
author={Doo Hwa HONG, June Sig SUNG, Kyung Hwan OH, Nam Soo KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Outlier Detection and Removal for HMM-Based Speech Synthesis with an Insufficient Speech Database},
year={2012},
volume={E95-D},
number={9},
pages={2351-2354},
abstract={Decision tree-based clustering and parameter estimation are essential steps in the training part of an HMM-based speech synthesis system. These two steps are usually performed based on the maximum likelihood (ML) criterion. However, one of the drawbacks of the ML criterion is that it is sensitive to outliers which usually result in quality degradation of the synthesized speech. In this letter, we propose an approach to detect and remove outliers for HMM-based speech synthesis. Experimental results show that the proposed approach can improve the synthetic speech, particularly when the available training speech database is insufficient.},
keywords={},
doi={10.1587/transinf.E95.D.2351},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Outlier Detection and Removal for HMM-Based Speech Synthesis with an Insufficient Speech Database
T2 - IEICE TRANSACTIONS on Information
SP - 2351
EP - 2354
AU - Doo Hwa HONG
AU - June Sig SUNG
AU - Kyung Hwan OH
AU - Nam Soo KIM
PY - 2012
DO - 10.1587/transinf.E95.D.2351
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2012
AB - Decision tree-based clustering and parameter estimation are essential steps in the training part of an HMM-based speech synthesis system. These two steps are usually performed based on the maximum likelihood (ML) criterion. However, one of the drawbacks of the ML criterion is that it is sensitive to outliers which usually result in quality degradation of the synthesized speech. In this letter, we propose an approach to detect and remove outliers for HMM-based speech synthesis. Experimental results show that the proposed approach can improve the synthetic speech, particularly when the available training speech database is insufficient.
ER -
English
