POS Tagging versus Classes in Language Modeling
Peter A. Heeman · 1998
Language models for speech recognition concentrate solely on recognizing the words that were spoken. In this paper, we advocate redefining the speech recognition problem so that its goal is to find both the best sequence of words and their POS tags, and thus incorporate POS tagging. The use of POS tags allows more sophisticated generalizations than are afforded by using a class-based approach. Furthermore, if we want to incorporate speech repair and intonational phrase modeling into the language model, using POS tags rather than classes gives better performance in this task. 1 Introduction For recognizing spontaneous speech, the acoustic signal is to weak to narrow down the number of word candidates. Hence, speech recognizers employ a language model that prunes out acoustic alternatives by taking into account the previous words that were recognized. In doing this, the speech recognition problem is viewed as finding the most likely word sequence W given the acoustic signal (Jelinek,...