Learning improved linear transforms for speech recognition
Abstract: This paper explores a large margin approach to learning a
linear transform for dimensionality reduction. The method assumes a trained Gaussian
mixture model for the each class to be discriminated and trains a linear transform with
respect to the model using stochastic gradient descent. Results are presented showing
improvements in state classification for individual frames and reduced word error rate
in a large vocabulary speech recognition problem after maximum likelihood training and
boosted maximum mutual information training.