[en] In this paper, we introduce MAGE/pHTS: a new software library for using HMM-based speech synthesis in reactive programming environments. MAGE/pHTS is based on the pHTS synthesis engine, a modified version of HTS that we developed and that enables the computation of speech audio samples on a 2-label window instead of the whole sentence. MAGE brings a realtime audio architecture on the top of pHTS and a user-friendly API for developers to integrate reactive speech synthesis in their applications. Finally we present some prototypes that have been developed, fol- lowing that process, and using various user interfaces to control speech synthesis.
Disciplines :
Mathematics
Author, co-author :
Astrinaki, Maria ; Université de Mons > Faculté Polytechnique > Information, Signal et Intelligence artificielle
D'alessandro, Nicolas ; Université de Mons > Faculté Polytechnique > Information, Signal et Intelligence artificielle
Dutoit, Thierry ; Université de Mons > Faculté Polytechnique > Information, Signal et Intelligence artificielle
Language :
English
Title :
MageFaceOSC: Performative Speech Synthesis Based On Realtime Face Tracking
Publication date :
01 March 2012
Journal title :
Quarterly Progress Scientific Report of the Numediart Research Program
ISSN :
2032-5398
Publisher :
numediart Institute for Creative Technologies, Mons, Belgium
Volume :
5
Issue :
1
Pages :
15-16
Research unit :
F105 - Information, Signal et Intelligence artificielle
Research institute :
R450 - Institut NUMEDIART pour les Technologies des Arts Numériques
