Speech Interface for Name Input based on Combination of Recognition Methods Using Syllable-based N-gram and Word Dictionary

摘要

We propose an interface for a name input based on speech recognition using syllable-based N-gram and a word dictionary. Name utterance is hard to recognize accurately because of the large vocabulary size, so the system uses continuous syllable recognition with syllable-based N-gram and isolated word recognition with a dictionary containing frequent words. User first utters a name and then chooses the correct word/syllables by pen touch from word/syllable candidates which were obtained from speech recognition. System displays word candidates, syllable sequence candidates and a syllable lattice on a touch panel and user can select a desired word from the candidates. We evaluated this interface. User could find the correct answer from word candidates or syllable sequence candidates at a rate of 82-86%, and could input correct name at a rate of 94-96% using syllable selection from the syllable lattice. Some subjects used this interface and felt that it was efficient and useful.