Hidden Markov Models in Speech and Language Processing

Abstract

Speech is an acoustic representation of a word or sequence of words, characterized by a slowly changing spectral envelope. Humans perceive this spectral envelope, and convert it into the underlying word string and its associated meaning. The ultimate goal of speech and language processing is to mimic this process so that a machine can hold a natural conversation with a human. Speech and language processing has a far wider role to play, however, in performing less complex tasks such as transcription, language identification, or audio document retrieval, all of which are feasible to a certain extent now. The basic step in all of these systems is to perform the inverse mapping of the speech into the underlying sequence of symbols, usually words, that produced it, as shown in Fig. 2.1. This chapter describes a statistical approach to solving the automatic speech recognition problem, based on stochastic Markov process models.