5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

ProSynth: An Integrated Prosodic Approach to Device-Independent, Natural-Sounding Speech Synthesis

Sarah Hawkins (1), Jill House (2), Mark Huckvale (2), John Local (3), Richard Ogden (3)

(1) University of Cambridge, UK
(2) University College London, UK
(3) University of York, UK

This paper outlines ProSynth, an approach to speech synthesis which takes a rich linguistic structure as central to the generation of natural-sounding speech. We start from the assumption that the speech signal is informationally rich, and that this acoustic richness reflects linguistic structural richness and underlies the percept of naturalness. Naturalness achieved by structural richness produces a perceptually robust signal intelligible in adverse listening conditions. ProSynth uses syntactic and phonological parses to model the fine acoustic-phonetic detail of real speech, segmentally, temporally and intonationally.

Full Paper

Bibliographic reference.  Hawkins, Sarah / House, Jill / Huckvale, Mark / Local, John / Ogden, Richard (1998): "Prosynth: an integrated prosodic approach to device-independent, natural-sounding speech synthesis", In ICSLP-1998, paper 0538.