Computing prosodic properties in a data-to-speech system

M. Theune, E.A.M. Klabbers, J.E.J.M. Odijk, J.R. Pijper, de

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    2 Downloads (Pure)

    Abstract

    We propose a set of rules for the computation of prosody which are implemented in an existing generic Data-to-Speech system. The rules make crucial use of both sentence-internal and sentence-external semantic and syntactic information provided by the system. In a Textto -Speech system, this information would have to be obtained through text analysis, but in Data-to-Speech it is readily available, and its reliable and detailed character makes it possible to compute the prosodic properties of generated sentences in a sophisticated way. This in turn allows for a close control of prosodic realization, resulting in natural-sounding intonation.
    Original languageEnglish
    Title of host publicationProceedings of the Workshop on Concept to Speech Generation Systems, Madrid, Spain, July 11
    EditorsK. Alter, H. Pirker, W. Finkler
    Pages39-45
    Publication statusPublished - 1997

    Fingerprint Dive into the research topics of 'Computing prosodic properties in a data-to-speech system'. Together they form a unique fingerprint.

    Cite this