Speech enhanced multi-span language model

To capture local and global constraints in a language, statistical n-grams are used in combination with multi-span language models for improved language modelling. Use of latent semantic analysis (LSA) to capture the global semantic constraints and bigram models to capture local constraints, is shown to reduce the perplexity of the model. In this paper we propose a method in which the multi-span LSA language model can be developed based on the speech signal. Reference pattern vectors are derived from the speech signal for each word in the vocabulary. Based on the normalised distance between the reference word pattern vector and the pattern vector of a word in the training data, the LSA model is developed. We show that this model in combination with a standard bigram model performs better than the conventional bigram + LSA model. The results are demonstrated for a limited vocabulary on a database for the Indian language, Tamil.