Prosody modification and Fujisaki´s model: Preserving natural soundness

Control of prosodic characteristics is one of the most important problems in the area of speech synthesis. Fujisaki´s model is probably the best model for pitch variations and its inversion is suitable for being integrated within speech synthesizres. This paper proposes a speech synthesis method based on Fujisaki´s model (combined direct and inverse modeling) in order to preserve natural soundness of synthesized speech. The idea is to modify a pitch contour on the basis of Fujisaki´s features and a reference contour. Experimental results have shown that using constraints related to Fujisaki´s model guarantees good natural-sounding speech synthesis.