Optimization of mel-cepstrum for speech recognition

Author

Hyun, Donghoon ; Lee, Chulhee

Author_Institution

Dept. of Electr. & Comput. Eng., Yonsei Univ., Seoul, South Korea

Volume

1

fYear

1999

fDate

1999

Firstpage

500

Abstract

In this paper we propose a method to optimize the performance of mel-cepstrum that is widely used in speech recognition. Typically, mel-cepstrum is obtained by critical band filters. Thus, the characteristics of filters determine mel-cepstrum, resulting in different performance. By changing the characteristics of filters such as shape, center frequency, and bandwidth, we analyze the performance of mel-cepstrum. Then we propose an algorithm to optimize the filters using the simplex method. Experiments with Korean digit words show that the recognition rate can be improved about 3-5%

Keywords

cepstral analysis; feature extraction; speech recognition; Korean digit words; critical band filters; filter bandwidth; filter center frequency; filter shape; mel-cepstrum performance optimisation; recognition rate; simplex method; speech recognition; Bandwidth; Cepstrum; Feature extraction; Filters; Frequency; Humans; Optimization methods; Shape; Signal generators; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on

Conference_Location

Tokyo

ISSN

1062-922X

Print_ISBN

0-7803-5731-0

Type

conf

DOI

10.1109/ICSMC.1999.814142

Filename

814142