Low bit quantization of the smoothed group delay spectrum for speech recognition

Author

Singer, Harald ; Umezaki, Taizo ; Itakura, Fumitada

Author_Institution

Dept. of Electr. Eng., Nagoya Univ., Japan

fYear

1990

fDate

3-6 Apr 1990

Firstpage

761

Abstract

The coefficients of the smoothed group delay spectrum (SGDS) are calculated by discrete-time Fourier transform of the linear prediction coefficients, i.e. the representation is in the frequency domain. Isolated word recognition experiments with a low bit quantization of these SGDS coefficients are reported. It is shown that recognition accuracy can be maintained using only 26 b/frame as compared to the conventional calculation with floating-point accuracy. Using a bark scale representation the error rate can be even further reduced

Keywords

encoding; fast Fourier transforms; spectral analysers; speech recognition; FFT; LPC; bark scale representation; discrete-time Fourier transform; linear prediction coefficients; low bit quantization; recognition accuracy; smoothed group delay spectrum; speech recognition; Accuracy; Cepstral analysis; Cepstrum; Delay; Delay effects; Electric variables measurement; Error analysis; Fourier transforms; Frequency domain analysis; Frequency estimation; Linear predictive coding; Quantization; Smoothing methods; Speech analysis; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115907

Filename

115907