Sixth International Conference on Spoken Language Processing (ICSLP 2000)

Beijing, China
October 16-20, 2000

Continuous Speech Recognition with Parse Filtering

Ken Hanazawa, Shinsuke Sakai

Computer & Communication Media Research, NEC Corporation, Japan

We propose "parse-filtering", a new approach to continuous speech recognition. With it, word sequence hypotheses generated on the basis of N-gram language models are verified by grammar-based parsing during the search for the best-scoring hypothesis, and unparsable hypotheses are filtered out immediately as the search proceeds. Experimental results show that this method yields a higher sentence accuracy than can be achieved with a trigram language model alone. Error reductions are, respectively, 10.0% for word error rate and 12.3% for sentence error rate.


Full Paper

Bibliographic reference.  Hanazawa, Ken / Sakai, Shinsuke (2000): "Continuous speech recognition with parse filtering", In ICSLP-2000, vol.1, 262-265.