The Speech Recognition System Based On Bark Wavelet MFCC

Author

Zhang, Xue-ying ; Bai, Jing ; Liang, Wu-zhou

Author_Institution

Coll. of Inf. Eng., Taiyuan Univ. of Technol.

Volume

1

fYear

2006

fDate

16-20 2006

Abstract

Bark wavelet is a new wavelet which is especially designed for speech signal. Its base function satisfies time and bandwidth product least. Moreover, the Bark wavelet divides frequency band based on auditory model. This paper uses Bark wavelet in MFCC. It was used to make preprocessing before FFT. On the other hand, it was used to instead of DCT in MFCC for overcoming the DCT´s disadvantage of fixed time-frequency resolution. Thus, a kind of good anti-noisy speech feature coefficient was obtained. Experimental results of speech recognition demonstrate that this new feature is more robust than the MFCC feature in noise environment and large vocabulary

Keywords

feature extraction; speech recognition; time-frequency analysis; wavelet transforms; Bark wavelet MFCC; anti-noisy speech feature coefficient; auditory model; speech recognition system; speech signal; time-frequency resolution; Bandwidth; Discrete cosine transforms; Frequency conversion; Mel frequency cepstral coefficient; Noise robustness; Signal design; Speech recognition; Time frequency analysis; Vocabulary; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing, 2006 8th International Conference on

Conference_Location

Beijing

Print_ISBN

0-7803-9736-3

Electronic_ISBN

0-7803-9736-3

Type

conf

DOI

10.1109/ICOSP.2006.345539

Filename

4128954