5th International Conference on Spoken Language Processing
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.
Bibliographic reference. Tsukada, Hajime / Yamamoto, Hirofumi / Takezawa, Toshiyuki / Sagisaka, Yoshinori (1998): "Grammatical word graph re-generation for spontaneous speech recognition", In ICSLP-1998, paper 0485.