Intonation by rule in text-to-speech applications

René Collier, Jacques Terken

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

    Abstract

    The high degree of standardization that can be achieved in the intonational synthesis by rule of isolated utterances may not be applicable to that of longer texts, because the listener may become aware of the unnatural recurrence of invariably the same melodic recipe. Two experiments were run in which listeners evaluated the naturalness of a prose text that had been intoned with varying degrees of melodic standardization.

    Original languageEnglish
    Title of host publicationEuropean Conference on Speech Technology, Edinburgh, September 1987 : [proceedings]
    EditorsJ. Laver, M.A. Jack
    Place of PublicationEdinburgh
    PublisherCEP consultants
    Pages165-168
    Number of pages4
    VolumeII
    ISBN (Print)0905941241, 9780905941240
    Publication statusPublished - 1987
    Event1987 European Conference on Speech Technology, ECST 1987 - Edinburgh, United Kingdom
    Duration: 1 Sept 19874 Sept 1987

    Conference

    Conference1987 European Conference on Speech Technology, ECST 1987
    Country/TerritoryUnited Kingdom
    CityEdinburgh
    Period1/09/874/09/87

    Bibliographical note

    Publisher Copyright:
    © European Conference on Speech Technology, ECST 1987. All rights reserved.

    Fingerprint

    Dive into the research topics of 'Intonation by rule in text-to-speech applications'. Together they form a unique fingerprint.

    Cite this