Title :
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
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;
Conference_Titel :
Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on
Conference_Location :
Pacific Grove, CA, USA
Print_ISBN :
0-8186-7646-9
DOI :
10.1109/ACSSC.1996.601153
