Feature extraction for automatic speech recognition (ASR)

Author

Swartz, Bill ; Magotra, Neeraj

Author_Institution

Dept. of Electr. Eng. & Comput. Eng., New Mexico Univ., Albuquerque, NM, USA

Volume

1

fYear

1996

fDate

3-6 Nov. 1996

Firstpage

748

Abstract

This paper presents a new speech feature extraction technique for use in automatic speech recognition (ASR). The technique is based on a new two-dimensional series expansion that is applied to the spectrogram of a sampled speech signal. The series expansion allows for global analysis in frequency and local multiresolution analysis in time. Multiresolution analysis in time is useful because the duration of vowels is almost an order of magnitude greater than that of consonants.

Keywords

Fourier series; feature extraction; signal resolution; spectral analysis; speech processing; speech recognition; wavelet transforms; automatic speech recognition; consonant duration; discrete time Fourier series; discrete time wavelet series; feature extraction; global analysis; local multiresolution analysis; sampled speech signal; spectrogram; two-dimensional series expansion; vowel duration; Automatic speech recognition; Cepstral analysis; Cepstrum; Equations; Feature extraction; Fourier series; Frequency; Multiresolution analysis; Shape measurement; Spectrogram;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-7646-9

Type

conf

DOI

10.1109/ACSSC.1996.601153

Filename

601153