A study on speaker adaptation of large vocabulary

Author

Jeon, Byoungwoo ; Kim, J. ; Hong, S. ; Kwon, Y. ; Lee, K.

Author_Institution

Dept. of Phys., Hanyang Univ., Ansan, South Korea

Volume

1

fYear

2001

fDate

2001

Firstpage

513

Abstract

In this paper, the authors propose a speaker adaptation algorithm. There can be a difference of recognition result by a speaker´s characteristics although a speaker independent system has a overall good performance. MAP (maximum a posterior) formulation is developed to adapt the characteristics of a speaker with estimation of the HMM (hidden Markov model) parameters from the training data. The proposed adaptation algorithm is evaluated in a large-vocabulary continuous speech recognition. In the experiment, the authors compare the recognition accuracy of the adapted acoustic models. In the experimental results, the MAP algorithm achieves up to about 40% additional reduction of error in phoneme recognition

Keywords

hidden Markov models; maximum likelihood estimation; parameter estimation; speaker recognition; MAP algorithm; hidden Markov model parameters estimation; large vocabulary speaker adaptation; large-vocabulary continuous speech recognition; maximum a posterior formulation; phoneme recognition; recognition accuracy; speaker adaptation algorithm; training data; Bayesian methods; Character recognition; Hidden Markov models; Kernel; Loudspeakers; Physics; Probability; Speech recognition; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics, 2001. Proceedings. ISIE 2001. IEEE International Symposium on

Conference_Location

Pusan

Print_ISBN

0-7803-7090-2

Type

conf

DOI

10.1109/ISIE.2001.931845

Filename

931845