- Connexion -
"MeLos: Analysis and Modelling of Speech Prosody and Speaking Style." June 23.
This thesis addresses the issue of modelling speech prosody for speech synthesis and presents MeLos: a complete system for the analysis and modelling of speech prosody, "the music of speech".
The objective of this thesis is to model the strategy, alternatives, and speaking style of a speaker for natural, expressive, and varied speech synthesis. The present study presents original contributions with special attention paid to the combination of theoretical linguistic and statistical modelling to provide a complete speech prosody system.
A unified discrete/continuous context-dependent HMM is presented to model the symbolic and the acoustic characteristics of speech prosody:
The proposed system is used to model the strategies, alternatives and speaking style of a speaker, and is extended to model the speaking style of any arbitrary number of speakers using shared-context-dependent modelling and speaker normalization techniques.
Keywords: speech prosody, speaking style, speech synthesis, discrete/continuous HMMs, stylization, trajectory modelling, linguistic analysis
Nick Campbell (Professor, CLCS - University of Dublin) reviewer
Simon King (Professor, CSTR - University of Edinburgh) reviewer
Jean-François Bonastre (Professor, LIA - University of Avignon) examiner
Eric de la Clergerie (Researcher, INRIA - ALPAGE) examiner
David Wessel (Professor, CNMAT - University of California Berkeley) examiner
Jean-Luc Zarader (Professor, ISIR - University of Paris VI) examiner
Anne Lacheret (Professor, MoDyCo - University of Paris Ouest - La Défense) supervisor
Xavier Rodet (Emeritus Researcher, IRCAM - University of Paris VI) supervisor