Feature Pruning for Fast Likelihood Evaluation of Automatic Speech Recognition

Abstract

This work presents feature pruning, a simple yet effective technique to reduce the likelihood computation in ASR systems that use continuous density HMMs. Our technique, under certain conditions, only evaluates the likelihoods of a fraction of feature elements, and approximates those of the remaining (pruned) ones by prediction. The order in which feature… (More)

Topics

4 Figures and Tables

Cite this paper

@inproceedings{LiFeaturePF, title={Feature Pruning for Fast Likelihood Evaluation of Automatic Speech Recognition}, author={Xiao Li and Jeff A. Bilmes} }