Rapid match training for large vocabularies

Abstract

This paper describes a new algorithm for building rapid match models for use in Dragon's continuous speech recognizer. Rather than working from a single representative token for each word, the new procedure works directly from a set of trained hidden Markov models. By simulated traversals of the HMMs, we generate a collection of sample tokens for each word which are then averaged together to build new rapid match models. This method enables us to construct models which better reflect the true variation in word occurrences and which no longer require the extensive adaptation needed in our original method. In this preliminary report, we outline this new procedure for building rapid match models and report results from initial testing on the Wall Street Journal recognition task.

Large Vocabulary Recognition of Wall Street Journal Sentences at Dragon Systems

“…Similarly, most of the pruning errors have been eliminated by running with a high threshold. A companion paper [10], that appears in this volume, describes a new strategy for training the rapid match models directly from the IIidden Markov Models specified by the PICs. This new strategy shows promise for reducing the average length of the rapid match list that must be returned at any given time, and thus, speeding up the recognizer.…”