Implementation and testing of a system for producing emotion-by-rule in synthetic speech

Iain R. Murray, John L. Arnott

    Research output: Contribution to journalArticle

    107 Citations (Scopus)

    Abstract

    A system is described which adds simulated emotion effects to synthetic speech. The control parameters of a speech synthesizer are controlled by rule in order to simulate the features of emotion expressed in the human voice. The system can simulate six vocal emotions and was evaluated with naïve listeners. The results indicated that the system was producing recognizable vocal emotions, with perception rankings similar to those found by previous research on human emotional speech. This system has been developed for use in voice prosthesis systems for non-vocal disabled persons, although it could be used to enhance any application which uses rule-based synthetic speech.
    Original languageEnglish
    Pages (from-to)369-390
    Number of pages22
    JournalSpeech Communication
    Volume16
    Issue number4
    DOIs
    Publication statusPublished - Jun 1995

    Fingerprint Dive into the research topics of 'Implementation and testing of a system for producing emotion-by-rule in synthetic speech'. Together they form a unique fingerprint.

  • Cite this