We propose a novel recognition method for generating an accurate grammatical word-graph allowing grammatical deviations. Our method uses both an n-gram and a grammar-based statistical language model and aligns utterances with the grammar by adding deviation information during the search process. Our experiments confirm that the word-graph obtained by our proposed method is superior to the one obtained by only using the n-gram with the same word-graph density. In addition, our recognition method can search enormous hypotheses more efficiently than the conventional word-graph based search method.
Cite as: Tsukada, H., Yamamoto, H., Takezawa, T., Sagisaka, Y. (1998) Grammatical word graph re-generation for spontaneous speech recognition. Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998), paper 0485, doi: 10.21437/ICSLP.1998-619
@inproceedings{tsukada98_icslp,
author={Hajime Tsukada and Hirofumi Yamamoto and Toshiyuki Takezawa and Yoshinori Sagisaka},
title={{Grammatical word graph re-generation for spontaneous speech recognition}},
year=1998,
booktitle={Proc. 5th International Conference on Spoken Language Processing (ICSLP 1998)},
pages={paper 0485},
doi={10.21437/ICSLP.1998-619}
}