Abstract

. In this paper we present an efficient data structure for storing trigram, bigram and unigram counts. The amount of memory required has been reduced by 53% compared to straightforward approaches. The average access time for retrieving information from the data structure has also slightly been reduced. Based upon this special data structure we have implemented several types of language models and applied them to the North American Business (NAB '94) recognition task. We show that both, the perplexity and the error rate could be reduced compared to the official NAB '94 trigram language model. 1 INTRODUCTION The main task of statistical language modelling is to provide a speech recognition system with the a-priori probabilities for a word sequence w 1 :::w N . In order to be able to compute the widely used bigram and trigram language models, we have to count how often a trigram or bigram, i.e. a word triple or a word pair, has been seen in a training corpus. We can then compute...

Citations