Effects of speaking rate and word frequency on pronunciations in convertional speech

Automatic speech recognition (ASR) systems typically have a static dictionary of word pronunciations for matching acoustic models to words. In this work, we argue that, in fact, pronunciations in spontaneous speech are dynamic and that ASR systems should change models in accordance with contextual factors. Two variables, speaking rate and word frequency, should be particularly promising for determining dynamic pronunciations, according to the linguistic literature. We analyze the relationship between these factors and realized pronunciations through a statistical exploration of the e€ects of these factors at the word, syllable, and phone levels in the Switchboard corpus. Both increased speaking rate and word likelihood can induce a signi®cant shift in probabilities of the pronunciations of frequent words. However, the interplay between all of these variables in the realization of pronunciations is complex. We also con®rm the intuition that variations in these factors correlate with changes in ASR system performance for both the Switchboard and Broadcast News corpora. Ó 1999 Elsevier Science B.V. All rights reserved.