Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

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

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
3 Author(s)
Beutler, R. ; Comput. Eng. & Networks Lab., ETH Zurich ; Kaufmann, T. ; Pfister, B.

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 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

Published in:

Automatic Speech Recognition and Understanding, 2005 IEEE Workshop on

Date of Conference:

27-27 Nov. 2005