Speaker-independent continuous-speech recognition by phoneme-based word spotting and time-synchronous context-free parsing

Abstract

This paper proposes a new continuous-speech recognition method by phoneme-based word spotting and time-synchronous context-free parsing. The word pattern is composed of the concatenation of phoneme patterns. The knowledge of syntax is given in Backus normal form. Therefore, our method is task-independent in terms of reference patterns and task language. The system first spots word candidates in an input sentence, and then generates a word lattice. The word spotting is performed by a dynamic time-warping method. Secondly, it selects the best word sequences found in the word lattice from all possible sentences which are defined by a context-free grammar. We propose two time-synchronous context-free parsing algorithms. One is time-synchronous in terms of the ending times of spotted words. This is an extension of the augmented continuous DP algorithm proposed by the author. The other is time-synchronous in terms of the ending times of generated partial sentences. The latter algorithm predicts the words following a partial sentence and then concatenates a spotted word found in the set of predicted words and the partial sentence. We applied the above algorithms to the continuous speech of English sentences which were related to “electronic mail” and confirmed that it worked well.