Eighth ISCA Workshop on Speech Synthesis

Barcelona, Catalonia, Spain
August 31-September 2, 2013

Mage - HMM-based Speech Synthesis Reactively Controlled by the Articulators

Maria Astrinaki (1), Alexis Moinet (1), Junichi Yamagishi (2,3), Korin Richmond (2), Zhen-Hua Ling (4), Simon King (2), Thierry Dutoit (1)

(1) TCTS Lab., Numediart Institute, University of Mons, Belgium
(2) University of Edinburgh, UK
(3) National Institute of Informatics, Tokyo, Japan
(4) University of Science and Technology of China (USTC), China

In this paper, we present the recent progress in the MAGE project. MAGE is a library for realtime and interactive (reactive) parametric speech synthesis using hidden Markov models (HMMs). Here, it is broadened in order to support not only the standard acoustic features (spectrum and f0 ) to model and synthesize speech but also to combine acoustic and articulatory features, such as tongue, lips and jaw positions. Such an integration enables the user to have a straight forward and meaningful control space to intuitively modify the synthesized phones in real time only by configuring the position of the articulators. Index Terms: speech synthesis, reactive, articulators

Full Paper

Bibliographic reference.  Astrinaki, Maria / Moinet, Alexis / Yamagishi, Junichi / Richmond, Korin / Ling, Zhen-Hua / King, Simon / Dutoit, Thierry (2013): "Mage - HMM-based speech synthesis reactively controlled by the articulators", In SSW8, 243.