Speech parameters vector based on arithmetic fourier transform

Author

Bovbel, Evgeny I. ; Kheidorov, Igor E.

Author_Institution

Dept. of Radiophys., Belarusicm State Univ., Minsk, Belarus

fYear

1998

fDate

8-11 Sept. 1998

Firstpage

1

Lastpage

3

Abstract

This paper is devoted to the developing of speech character vector based on the arithmetic Fourier transform for speech recognition tasks. The calculation complexity and accuracy of three spectrum methods- fast Fourier transform (FFT), linear prediction (LP) method and arithmetic Fourier transform (AFT) were estimated. It was found that AFT is very useful to calculate speech mel-parameters and provides a simple parallel VLSI realization. If to apply the cos transformation for the AFT mel-spectral parameters we achieve robust parameters for speech signal variations. As a result of the researches the speech parameter vector based on AFT coefficients was designed.

Keywords

VLSI; fast Fourier transforms; speech recognition; AFT mel-spectral parameters; FFT; LP method; arithmetic Fourier transform; cos transformation; fast Fourier transform; linear prediction method; parallel VLSI realization; speech character vector; speech parameter vector; speech recognition task; Fourier series; Fourier transforms; Robustness; Spectral analysis; Speech; Speech recognition; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Conference (EUSIPCO 1998), 9th European

Conference_Location

Rhodes

Print_ISBN

978-960-7620-06-4

Type

conf

Filename

7090117