Speech recognition using syllable-like units

It is well known that speech is dynamic and that frame-based systems lack the ability to realistically model the dynamics of speech. Segment-based systems offer the potential to integrate the dynamics of speech, at least within the phoneme boundaries, although it is difficult to obtain accurate phonemic segmentation in fluent speech. In this paper we propose a new approach which uses syllable-like units in recognition. In the proposed approach, syllable-like units are defined by rules and used as the basic units of recognition. The motivation for using syllable-like units is (1) by modeling perceptually more meaningful units, better modeling of speech can be achieved; and (2) this method provides a better framework for incorporating dynamic modeling techniques into the recognition system. The proposed approach has achieved the same recognition performance on the task of recognizing months of the year as compared to the best frame-based recognizer available.