Robust speech feature extraction by growth transformation in reproducing kernel Hilbert space

Author

Chakrabartty, Shantanu ; Deng, Yunbin ; Cauwenberghs, Gert

Author_Institution

Center for Language & Speech Process., Johns Hopkins Univ., Baltimore, MD, USA

Volume

1

fYear

2004

fDate

17-21 May 2004

Abstract

A robust speech feature extraction procedure, by kernel regression nonlinear predictive coding, is presented. Features maximally insensitive to additive noise are obtained by growth transformation of regression functions spanning a reproducing kernel Hilbert space (RKHS). Experiments on TI-DIGIT demonstrate consistent robustness of the new features to noise of varying statistics, yielding significant improvements in digit recognition accuracy over identical models trained using Mel-scale cepstral features and evaluated at noise levels between 0 and 30 dB SNR.

Keywords

Hilbert spaces; feature extraction; nonlinear codes; regression analysis; speech coding; speech recognition; TI-DIGIT; additive noise insensitivity; digit recognition accuracy; growth transformation; kernel regression nonlinear predictive coding; reproducing kernel Hilbert space; robust speech feature extraction; Additive noise; Cepstral analysis; Feature extraction; Hilbert space; Kernel; Noise level; Noise robustness; Predictive coding; Speech coding; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8484-9

Type

conf

DOI

10.1109/ICASSP.2004.1325940

Filename

1325940