Continuous Speech Recognition Using a Combination of Syntactic Constraints and Dependency Relationships

Tsuyoshi MORIMOTO

Summary :

This paper proposes a Japanese continuous speech recognition mechanism in which a full-sentence-level context-free-grammar (CFG) and one kind of semantic constraint called dependency relationships between two bunsetsu (a kind of phrase) in Japanese" are used during speech recognition in an integrated way. Each dependency relationship is a modification relationship between two bunsetsu; these relationships include the case-frame relationship of a noun bunsetsu to a predicate bunsetsu, or adnominal modification relationships such as a noun bunsetsu to a noun bunsetsu. To suppress the processing overhead caused by using relationships of this type during speech recognition, no rigorous semantic analysis is performed. Instead, a simple matching with examples" approach is adopted. An experiment was carried out and results were compared with a case employing only CFG constraints. They show that the speech recognition accuracy is improved and that the overhead is small enough.

• Publication: IEICE TRANSACTIONS on Information Vol.E79-D No.1 pp.54-62
• Publication Date: 1996/01/25
• Type of Manuscript: PAPER
• Category: Speech Processing and Acoustics

Authors

Tsuyoshi MORIMOTO

Keyword

continuous speech recognition,  language model,  integration of speech and language,  dependency relationship