On the use of probabilistic grammars in speech annotation and segmentation tasks

The present paper explores the issue of corpus prosodic parsing in terms of prosodic words. This question is of importance in both speech processing and corpus annotation studies. We propose a method grounded on both statistical and symbolic (phonological) representations of tonal phenomena and we have recourse to probabilistic grammars, whithin which we implement a minimal prosodic hierarchical structure. Both the stages of probabilistic grammar building and its testing in prediction are explored and quantively and qualitatively evaluated.