Cepstral domain segmental nonlinear feature transformations for robust speech recognition

Author

Segura, José C. ; Benítez, Carmen ; de la Torre, A. ; Rubio, Antonio J. ; Ramirez, J.

Author_Institution

Dept. de Electron. y Tecnologia de Computadores, Univ. de Granada, Spain

Volume

11

Issue

5

fYear

2004

fDate

5/1/2004 12:00:00 AM

Firstpage

517

Lastpage

520

Abstract

This letter presents a new segmental nonlinear feature normalization algorithm to improve the robustness of speech recognition systems against variations of the acoustic environment. An experimental study of the best delay-performance tradeoff is conducted within the AURORA-2 framework, and a comparison with two commonly used normalization algorithms is presented. Computationally efficient algorithms based on order statistics are also presented. One of them is based on linear interpolation between sampling quantiles, and the other one is based on a point estimation of the probability distribution. The reduction in the computational cost does not degrade the performance significantly.

Keywords

cepstral analysis; interpolation; probability; speech recognition; statistics; AURORA-2 framework; acoustic environment; cepstral domain segmental nonlinear feature transformations; computational reduction; delay-performance tradeoff; linear interpolation; normalization algorithm; probability distribution; robust speech recognition; statistics; Cepstral analysis; Computational efficiency; Delay; Interpolation; Nonlinear acoustics; Probability distribution; Robustness; Sampling methods; Speech recognition; Statistical distributions;

fLanguage

English

Journal_Title

Signal Processing Letters, IEEE

Publisher

ieee

ISSN

1070-9908

Type

jour

DOI

10.1109/LSP.2004.826648

Filename

1288122