Integrating a non-probabilistic grammar into large vocabulary continuous speech recognition

R. Beutler, T. Kaufmann, B. Pfister
2005 IEEE Workshop on Automatic Speech Recognition and Understanding, 2005.  
We propose a method of incorporating a non-probabilistic grammar into large vocabulary continuous speech recognition (LVCSR). Our basic assumption is that the utterances to be recognized are grammatical to a sufficient degree, which enables us to decrease the word error rate by favouring grammatical phrases. We use a parser and a handcrafted grammar to identify grammatical phrases in word lattices produced by a speech recognizer. This information is then used to rescore the word lattice. We
more » ... ord lattice. We measured the benefit of our method by extending an LVCSR baseline system (based on hidden Markov models and a 4-gram language model) with our rescoring component. We achieved a statistically significant reduction in word error rate compared to the baseline system.
doi:10.1109/asru.2005.1566496 fatcat:mtx64cnhhfapzj6jty4sbmspzq