On the Use of Kernel PCA for Feature Extraction in Speech Recognition

Amaro LIMA  Heiga ZEN  Yoshihiko NANKAKU  Chiyomi MIYAJIMA  Keiichi TOKUDA  Tadashi KITAMURA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E87-D   No.12   pp.2802-2811
Publication Date: 2004/12/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Speech and Hearing
Keyword: 
kernel,  feature space,  principal component analysis,  feature extraction,  speech recognition,  

Full Text: PDF(425.6KB)>>
Buy this Article




Summary: 
This paper describes an approach to feature extraction in speech recognition systems using kernel principal component analysis (KPCA). This approach represents speech features as the projection of the mel-cepstral coefficients mapped into a feature space via a non-linear mapping onto the principal components. The non-linear mapping is implicitly performed using the kernel-trick, which is a useful way of not mapping the input space into a feature space explicitly, making this mapping computationally feasible. It is shown that the application of dynamic (Δ) and acceleration (ΔΔ) coefficients, before and/or after the KPCA feature extraction procedure, is essential in order to obtain higher classification performance. Better results were obtained by using this approach when compared to the standard technique.