|
Authors: | René Beutler, Tobias Kaufmann, Beat Pfister |
Group: | Computer Engineering |
Type: | Inproceedings |
Title: | Integrating a Non-Probabilistic Grammar into Large Vocabulary Continuous Speech Recognition |
Year: | 2005 |
Month: | November |
Pub-Key: | BKP05c |
Book Titel: | 2005 IEEE Automatic Speech Recognition and Understanding Workshop |
Pages: | 104-109 |
Keywords: | speech processing |
Abstract: | 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 hand-crafted 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. |
Location: | San Juan, Puerto Rico |
Resources: | [BibTeX] |