Current speech recognition systems require a lot of computational resources to decode an input utterance. Many efforts have been done in order to reduce these requirements. One of the techniques that is being explored is the fast phoneme look-ahead. The idea is to compute quickly approximate scores in order to prune little promising hypothesis. These scores are computed by using simple phone-like units and analysing an acoustic segment look-ahead.

In this paper, we describe and evaluate a language model using word classes automatically generated from a word clustering algorithm. Class based language models have been shown to be effective for rapid adaptation, training on small datasets, and reduced memory usage. In terms of model perplexity, prior work has shown diminished returns for class based language models constructed using very large training sets. This paper describes a method of using a class model as a backoff to a bigram model which produced significant benefits even when trained from a large text corpus. Tests results on the Whisper continuous speech recognition system show that for a given word error rate, the clustered bigram model uses 2/3 fewer parameters compared to a standard bigram model using unigram backoff.

In this study, we examine how fast decoding of conversational speech with large vocabularies profits from efficient use of linguistic information, i.e. language models and grammars. Based on a re-entrant single pronunciation prefix tree, we use the concept of linguistic context polymorphism to achieve an early incorporation of language model information. This approach allows us to use all available language model information in a one-pass decoder, using the same engine to decode with statistical n-gram language models as well as context free grammars or re-scoring of lattices in an efficient way.

proposed. The recognition system uses lexical trees and a bigram language model. The first part of this article is focused on voice assimilation phenomenon description, triphone lexical tree construction, and voice assimilation impact on LVCSR system performance. The second part outlines lexical tree decoding algorithm based on Viterbi search with pruning. Different methods of voice assimilation implementation are discussed. Key-Words:- voice assimilation, LVCSR system, lexical tree, bigram language model 1