EM training of finite-state transducers and its application to pronunciation modeling

Abstract

Recently, nite-state transducers (FSTs) have been shown to be useful for a number of applications in speech and language processing. FST operations such as composition, determinization, and minimization make manipulating FSTs very simple. In this paper, we present a method to learn weights for arbitrary FSTs using the EM algorithm. We show that this FST EM algorithm is able to learn pronunciation weights that improve the word error rate for a spontaneous speech recognition task.