Pauses and the temporal structure of speech

Abstract

Natural-sounding speech synthesis requires close control over the temporal structure of the speech flow. This includes a full predictive scheme for the durational structure and in particuliar the prolongation of final syllables of lexemes as well as for the pausal structure in the utterance. In this chapter, a description of the temporal structure and the summary of the numerous factors that modify it are presented. In the second part, predictive schemes for the temporal structure of speech ("performance structures") are introduced, and their potential for characterising the overall prosodic structure of speech is demonstrated.