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

S. Chakrabartty, Yunbin Deng, G. Cauwenberghs

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

The performance of speech recognition systems depends on consistent quality of the speech features across variable environmental conditions encountered during training and evaluation. This paper presents a kernel-based nonlinear predictive coding procedure that yields speech features which are robust to nonstationary noise contaminating the speech signal. Features maximally insensitive to additive noise are obtained by growth transformation of regression functions that span a reproducing kernel Hilbert space (RKHS). The features are normalized by construction and extract information pertaining to higher-order statistical correlations in the speech signal. Experiments with the TI-DIGIT database demonstrate consistent robustness 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 signal-to-noise ratio.

Original languageEnglish
Article number4276746
Pages (from-to)1842-1849
Number of pages8
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume15
Issue number6
DOIs
StatePublished - Aug 2007

Keywords

  • Feature extraction
  • Growth transforms
  • Noise robustness
  • Nonlinear signal processing
  • Reproducing kernel Hilbert Space
  • Speaker verification

Fingerprint

Dive into the research topics of 'Robust speech feature extraction by growth transformation in reproducing Kernel Hilbert space'. Together they form a unique fingerprint.

Cite this