Jointly Optimized Discriminative Features for Speech Recognition

In the past decade, methods to extract long-term acoustic features for speech recognition using Multi-Layer Perceptrons have been proposed. These features have been proved to be good complementary features in some feature augmentations and/or through system combination. Usually, conventional linear dimension reduction algorithms, e.g. Linear Discriminative Analysis, are not applied on the combined features. In this paper, Region Dependent Transform is applied to jointly optimize the feature combination under a discriminative training criterion. When compared to a conventional augmentation, 3% to 6% relative character error rate reduction for Mandarin speech recognition has been achieved using Region Dependent Transform.