Third-Order Moments of Filtered Speech Signals for Robust Speech Recognition

Document Type

Conference Proceeding

Language

eng

Format of Original

7 p.

Publication Date

4-20-2005

Publisher

Springer

Source Publication

International Conference on Non-Linear Speech Processing, NOLISP 2005, Barcelona, Spain, April 19-22, 2005, Revised Selected Papers

Source ISSN

0302-9743

Abstract

Novel speech features calculated from third-order statistics of subband-filtered speech signals are introduced and studied for robust speech recognition. These features have the potential to capture nonlinear information not represented by cepstral coefficients. Also, because the features presented in this paper are based on the third-order moments, they may be more immune to Gaussian noise than cepstrals, as Gaussian distributions have zero third-order moments. Experiments on the AURORA2 database studying these features in combination with Mel-frequency cepstral coefficients (MFCC’s) are presented, and some improvement over the MFCC-only baseline is shown when clean speech is used for training, though the same improvement is not seen when multi-condition training data is used.

Comments

Published as part of the proceedings of the International Conference on Non-Linear Speech Processing, NOLISP 2005, Barcelona, Spain, April 19-22, 2005, Revised Selected Papers, 2005: 151-157. DOI.

Share

COinS