Feature Pruning for Fast Likelihood Evaluation of Automatic Speech Recognition
Xiao Li, Jeff Bilmes · 2004
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 elements are evaluated is obtained by a data-driven approach to minimize computation. With this order, feature pruning can speed up the likelihood evaluation by a factor of 1.33 and reduce its power consumption by 27% for an isolated word recognition task. For a continuous speech recognition system using either monophone or triphone models, the speedup and power reduction of the likelihood evaluation are 1.50 and 35% respectively.