Data-driven temporal filters for robust features in speech recognition obtained via Minimum Classification Error (MCE)

Abstract

In deriving the data-driven temporal filters for speech features, the Linear Discriminant Analysis (LDA) and the Principal Component Analysis (PCA) have been shown to be successful in improving the feature robustness. In this paper, it's proposed that the criterion of Minimum Classification Error (MCE) can also be used to obtain the data-driven temporal… (More)
DOI: 10.1109/ICASSP.2002.5743732

Topics

3 Figures and Tables

Slides referencing similar topics