Robust speech recognition using data-driven temporal filters based on independent component analysis

In this paper, a data-driven temporal processing method based on Independent Component Analysis (ICA) is proposed for obtaining a more robust speech representation. Tw o different schemes of dominant temporal filters based on ICA are investigated. The one is the perceptually-based filter which always focuses on the modulation frequency range between 1 and 16 Hz and the other is the most independent component discovered by ICA algorithm. Detailed comparative analysis between the proposed ICA-derived temporal filters and the previous statistical methods including Linear Discriminant Analysis (LDA) and Principle Component Analysis (PCA) is presented. The preliminary experiments show that the performance of the ICA based temporalfiltering is much better in comparison with the LDA and PCA based methods in noisy environment.