A polynomial interpolation-based scheme for reducing bandwidth in distributed speech recognition system

Author

Touazi, Azzedine ; Debyeche, Mohamed

Author_Institution

Fac. of Electron. & Comput. Sci., Univ. of Sci. & Technol. Houari Boumedienne, Algiers, Algeria

fYear

2013

fDate

20-23 Oct. 2013

Firstpage

1

Lastpage

4

Abstract

In this paper, we propose a low bit-rate compression scheme in distributed speech recognition (DSR) system based on polynomial interpolation. Dimensionality reduction of a set of successive Mel frequency cepstral coefficients (MFCCs) is achieved by performing polynomial least squares fitting. A conventional vector quantization (VQ) is applied to the polynomial coefficients to achieve more than 58% of bandwidth reduction as compared to ETSI advanced front-end (ETSI-AFE) encoder. Evaluation performance has been conducted on the Aurora-2 database in clean and multi-condition training modes. With respect to ETSI-AFE, the results obtained with the proposed encoder show no significant degradation in term of overall recognition accuracy.

Keywords

least squares approximations; polynomial approximation; quantisation (signal); speech recognition; conventional vector quantization; dimensionality reduction; distributed speech recognition system; low bit rate compression scheme; mel frequency cepstral coefficients; polynomial coefficients; polynomial interpolation based scheme; polynomial least squares fitting; Bandwidth; Interpolation; Mel frequency cepstral coefficient; Polynomials; Speech recognition; Training; Vectors; Distributed speech recognition; ETSI-AFE; MFCC; polynomial least squares fitting; vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Applications of Signal Processing to Audio and Acoustics (WASPAA), 2013 IEEE Workshop on

Conference_Location

New Paltz, NY

ISSN

1931-1168

Type

conf

DOI

10.1109/WASPAA.2013.6701880

Filename

6701880