Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition
Summary :
This paper investigates the effectiveness of the DAEM (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the ML estimates, it has the problem of initialization dependence. To relax this problem, the DAEM algorithm has been proposed and confirmed the effectiveness in artificial small tasks. In this paper, we applied the DAEM algorithm to practical speech recognition tasks: speaker recognition based on GMMs and continuous speech recognition based on HMMs. Experimental results show that the DAEM algorithm can improve the recognition performance as compared to the standard EM algorithm with conventional initialization algorithms, especially in the flat start training for continuous speech recognition.
- Publication
- IEICE TRANSACTIONS on Information Vol.E88-D No.3 pp.425-431
- Publication Date
- 2005/03/01
- Publicized
- Online ISSN
- DOI
- 10.1093/ietisy/e88-d.3.425
- Type of Manuscript
- Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
- Category
- Feature Extraction and Acoustic Medelings
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
Yohei ITAYA, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA, "Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 3, pp. 425-431, March 2005, doi: 10.1093/ietisy/e88-d.3.425.
Abstract: This paper investigates the effectiveness of the DAEM (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the ML estimates, it has the problem of initialization dependence. To relax this problem, the DAEM algorithm has been proposed and confirmed the effectiveness in artificial small tasks. In this paper, we applied the DAEM algorithm to practical speech recognition tasks: speaker recognition based on GMMs and continuous speech recognition based on HMMs. Experimental results show that the DAEM algorithm can improve the recognition performance as compared to the standard EM algorithm with conventional initialization algorithms, especially in the flat start training for continuous speech recognition.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.3.425/_p
Copy
@ARTICLE{e88-d_3_425,
author={Yohei ITAYA, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition},
year={2005},
volume={E88-D},
number={3},
pages={425-431},
abstract={This paper investigates the effectiveness of the DAEM (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the ML estimates, it has the problem of initialization dependence. To relax this problem, the DAEM algorithm has been proposed and confirmed the effectiveness in artificial small tasks. In this paper, we applied the DAEM algorithm to practical speech recognition tasks: speaker recognition based on GMMs and continuous speech recognition based on HMMs. Experimental results show that the DAEM algorithm can improve the recognition performance as compared to the standard EM algorithm with conventional initialization algorithms, especially in the flat start training for continuous speech recognition.},
keywords={},
doi={10.1093/ietisy/e88-d.3.425},
ISSN={},
month={March},}
Copy
TY - JOUR
TI - Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 425
EP - 431
AU - Yohei ITAYA
AU - Heiga ZEN
AU - Yoshihiko NANKAKU
AU - Chiyomi MIYAJIMA
AU - Keiichi TOKUDA
AU - Tadashi KITAMURA
PY - 2005
DO - 10.1093/ietisy/e88-d.3.425
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2005
AB - This paper investigates the effectiveness of the DAEM (Deterministic Annealing EM) algorithm in acoustic modeling for speaker and speech recognition. Although the EM algorithm has been widely used to approximate the ML estimates, it has the problem of initialization dependence. To relax this problem, the DAEM algorithm has been proposed and confirmed the effectiveness in artificial small tasks. In this paper, we applied the DAEM algorithm to practical speech recognition tasks: speaker recognition based on GMMs and continuous speech recognition based on HMMs. Experimental results show that the DAEM algorithm can improve the recognition performance as compared to the standard EM algorithm with conventional initialization algorithms, especially in the flat start training for continuous speech recognition.
ER -
English
