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
Cite as: Astrinaki, M., Moinet, A., Yamagishi, J., Richmond, K., Ling, Z.-H., King, S., Dutoit, T. (2013) Mage - HMM-based speech synthesis reactively controlled by the articulators. Proc. 8th ISCA Workshop on Speech Synthesis (SSW 8), 243
@inproceedings{astrinaki13b_ssw,
author={Maria Astrinaki and Alexis Moinet and Junichi Yamagishi and Korin Richmond and Zhen-Hua Ling and Simon King and Thierry Dutoit},
title={{Mage - HMM-based speech synthesis reactively controlled by the articulators}},
year=2013,
booktitle={Proc. 8th ISCA Workshop on Speech Synthesis (SSW 8)},
pages={243}
}