GoalGetter: predicting contrastive accent in data-to-speech generation

    Research output: Contribution to conferencePaper

    9 Downloads (Pure)

    Abstract

    This paper addresses the problem of predicting contrastive accent in spoken language generation. The common strategy of accenting 'new' and deaccenting 'old' information is not sufficient to achieve correct accentuation: generation of contrastive accent is required as well. I will discuss a few approaches to the prediction of contrastive accent, and propose a practical solution which avoids the problems these approaches are faced with. These issues are discussed in the context of GoalGetter, a data-to-speech system which generates spoken reports of football matches on the basis of tabular information.
    Original languageEnglish
    Pages177-190
    Number of pages14
    Publication statusPublished - Nov 1996
    Event7th Meeting on Computational Linguistics in the Netherlands, CLIN 1996 - Institute for Perception Research (IPO), Eindhoven, Netherlands
    Duration: 15 Nov 199615 Nov 1996
    Conference number: 7
    http://odur.let.rug.nl/~vannoord/clin/Clin7/

    Conference

    Conference7th Meeting on Computational Linguistics in the Netherlands, CLIN 1996
    Abbreviated titleCLIN
    CountryNetherlands
    CityEindhoven
    Period15/11/9615/11/96
    Internet address

    Cite this

    Theune, M. (1996). GoalGetter: predicting contrastive accent in data-to-speech generation. 177-190. Paper presented at 7th Meeting on Computational Linguistics in the Netherlands, CLIN 1996, Eindhoven, Netherlands.