5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Use of High-Level Linguistic Constraints for Constructing Feature-Based Phonological Model in Speech Recognition

Jiping Sun, Li Deng

Department of Electrical and Computer Engineering, University of Waterloo, Canada

Modeling phonological units of speech is a critical issue in speech recognition. In this paper, we report our recent development of an overlapping feature-based phonological model which gives long-span contextual dependency. We extend our earlier work by incorporating high-level linguistic constraints in automatic construction of the feature overlapping patterns. The main linguistic information explored includes morpheme, syllable, syllable constituent categories and word stress markers. We describe a consistent computational framework developed for the construction of the feature-based model, and discuss use of the model as the HMM state topology for speech recognizers.

Full Paper

Bibliographic reference.  Sun, Jiping / Deng, Li (1998): "Use of high-level linguistic constraints for constructing feature-based phonological model in speech recognition", In ICSLP-1998, paper 0043.