A Study on Speaker Adaptation for Mandarin Syllable Recognition with Minimum Error Discriminative Training

Chih-Heng LIN; Chien-Hsing WU; Pao-Chung CHANG

A Study on Speaker Adaptation for Mandarin Syllable Recognition with Minimum Error Discriminative Training

Chih-Heng LIN, Chien-Hsing WU, Pao-Chung CHANG

Full Text Views

0

Share
Cite this

Summary :

This paper investigates a different method of speaker adaptation for Mandarin syllable recognition. Based on the minimum classification error (MCE) criterion, we use the generalized probabilistic decent (GPD) algorithm to adjust interatively the parameters of the hidden Markov models (HMM). The experiments on the multi-speaker Mandarin syllable database of Telecommunication Laboratories (T.L.) yield the following results: 1) Efficient speaker adaptation can be achieved through discriminative training using the MCE criterion and the GPD algorithm. 2) The computations required can be reduced through the use of the confusion sets in Mandarin base syllables. 3) For the discriminative training, the adjustment on the mean values of the Gaussian mixtures has the most prominent effect on speaker adaptation. 4) The discriminative training approach can be used to enhance the speaker adaptation capability of the maximum a posteriori (MAP) approach.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.6 pp.712-718

Publication Date: 1995/06/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Issue on Spoken Language Processing)

Category

Cite this

Copy

Chih-Heng LIN, Chien-Hsing WU, Pao-Chung CHANG, "A Study on Speaker Adaptation for Mandarin Syllable Recognition with Minimum Error Discriminative Training" in IEICE TRANSACTIONS on Information, vol. E78-D, no. 6, pp. 712-718, June 1995, doi: .
Abstract: This paper investigates a different method of speaker adaptation for Mandarin syllable recognition. Based on the minimum classification error (MCE) criterion, we use the generalized probabilistic decent (GPD) algorithm to adjust interatively the parameters of the hidden Markov models (HMM). The experiments on the multi-speaker Mandarin syllable database of Telecommunication Laboratories (T.L.) yield the following results: 1) Efficient speaker adaptation can be achieved through discriminative training using the MCE criterion and the GPD algorithm. 2) The computations required can be reduced through the use of the confusion sets in Mandarin base syllables. 3) For the discriminative training, the adjustment on the mean values of the Gaussian mixtures has the most prominent effect on speaker adaptation. 4) The discriminative training approach can be used to enhance the speaker adaptation capability of the maximum a posteriori (MAP) approach.
URL: https://globals.ieice.org/en_transactions/information/10.1587/e78-d_6_712/_p

Copy

@ARTICLE{e78-d_6_712,
author={Chih-Heng LIN, Chien-Hsing WU, Pao-Chung CHANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Study on Speaker Adaptation for Mandarin Syllable Recognition with Minimum Error Discriminative Training},
year={1995},
volume={E78-D},
number={6},
pages={712-718},
abstract={This paper investigates a different method of speaker adaptation for Mandarin syllable recognition. Based on the minimum classification error (MCE) criterion, we use the generalized probabilistic decent (GPD) algorithm to adjust interatively the parameters of the hidden Markov models (HMM). The experiments on the multi-speaker Mandarin syllable database of Telecommunication Laboratories (T.L.) yield the following results: 1) Efficient speaker adaptation can be achieved through discriminative training using the MCE criterion and the GPD algorithm. 2) The computations required can be reduced through the use of the confusion sets in Mandarin base syllables. 3) For the discriminative training, the adjustment on the mean values of the Gaussian mixtures has the most prominent effect on speaker adaptation. 4) The discriminative training approach can be used to enhance the speaker adaptation capability of the maximum a posteriori (MAP) approach.},
keywords={},
doi={},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - A Study on Speaker Adaptation for Mandarin Syllable Recognition with Minimum Error Discriminative Training
T2 - IEICE TRANSACTIONS on Information
SP - 712
EP - 718
AU - Chih-Heng LIN
AU - Chien-Hsing WU
AU - Pao-Chung CHANG
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 1995
AB - This paper investigates a different method of speaker adaptation for Mandarin syllable recognition. Based on the minimum classification error (MCE) criterion, we use the generalized probabilistic decent (GPD) algorithm to adjust interatively the parameters of the hidden Markov models (HMM). The experiments on the multi-speaker Mandarin syllable database of Telecommunication Laboratories (T.L.) yield the following results: 1) Efficient speaker adaptation can be achieved through discriminative training using the MCE criterion and the GPD algorithm. 2) The computations required can be reduced through the use of the confusion sets in Mandarin base syllables. 3) For the discriminative training, the adjustment on the mean values of the Gaussian mixtures has the most prominent effect on speaker adaptation. 4) The discriminative training approach can be used to enhance the speaker adaptation capability of the maximum a posteriori (MAP) approach.
ER -