Copy-synthesis of phrase-level utterances

This paper presents a simulation framework for synthesizing speech from anatomically realistic data of the vocal tract. The acoustic propagation paradigm is appropriately chosen so that it can deal with complex geometries and a time-varying length of the vocal tract. The glottal source model designed in this paper allows partial closure of the glottis by branching a posterior chink in parallel to a classic lumped mass-spring model of the vocal folds. Temporal scenarios for the dynamic shapes of the vocal tract and the glottal configurations may be derived from the simultaneous acquisition of X-ray images and audio recording. Copy synthesis of a few French sentences shows the accuracy of the simulation framework to reproduce acoustic cues of natural phrase-level utterances containing most of French natural classes while considering the real geometric shape of the speaker.