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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Amaro LIMA, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA, "On the Use of Kernel PCA for Feature Extraction in Speech Recognition" in IEICE TRANSACTIONS on Information,
vol. E87-D, no. 12, pp. 2802-2811, December 2004, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/e87-d_12_2802/_p
Copy
@ARTICLE{e87-d_12_2802,
author={Amaro LIMA, Heiga ZEN, Yoshihiko NANKAKU, Chiyomi MIYAJIMA, Keiichi TOKUDA, Tadashi KITAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={On the Use of Kernel PCA for Feature Extraction in Speech Recognition},
year={2004},
volume={E87-D},
number={12},
pages={2802-2811},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - On the Use of Kernel PCA for Feature Extraction in Speech Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 2802
EP - 2811
AU - Amaro LIMA
AU - Heiga ZEN
AU - Yoshihiko NANKAKU
AU - Chiyomi MIYAJIMA
AU - Keiichi TOKUDA
AU - Tadashi KITAMURA
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E87-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2004
AB - 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.
ER -