On the use of lattices for the automatic generation of pronunciations

Abstract

In this paper, we explore the use of lattices to generate pronunciations for speech recognition based on the observation of a few (say one or two) speech utterances of a word. Various search strategies are investigated in combination with schemes where single or multiple pronunciations are generated for each speech utterance. In our experiments, a strategy that combines merging time-overlapping links in a context-dependent subphone lattice and generating multiple pronunciations provides the best recognition accuracy. This results in average relative gains of 30% over the generation of single pronunciations using a Viterbi search.