Exploiting correlations among models with application to large vocabulary speech recognition

Abstract: "In a typical speech recognition system, computing the match between an incoming acoustic string and many competing models is computationally expensive. Once the highest ranking models are identified, all other match scores are discarded. We propose to make use of all computed scores by means of statistical inference. We view the match between an incoming acoustic string s and a model M[subscript i] as a random variable Y[subscript i]. The class-conditional distributions of (Y,...,Y[subscript N]) can be studied offline by sampling, and then used in a variety of ways. For example, the means of these distributions give rise to a natural measure of distance between models.One of the most useful applications of these distributions is as a basis for a new Bayesian classifier. The latter can be used to significantly reduce search effort in large vocabularies, and to quickly obtain a short list of candidate words. An example HMM-based system shows promising results."