Robust parsing for word lattices in Continuous Speech Recognition systems

One of the roles of a natural language processing (NLP) model in continuous speech recognition (CSR) systems is to find the best sentence hypothesis by ranking all n-best sentences according to the grammar. This paper describes a robust parsing algorithm for spoken language recognition (SLR) which utilizes a technique that improves the efficiency of parsing. This technique integrates grammatical and statistical approaches, and by using a best-first parsing strategy improves the accuracy of recognition. Preliminary experimental results using a Persian continuous speech recognition system show effective improvements in accuracy with little change in recognition time. The word error rate was also reduced by 18%.