Articulatory Speech Synthesis from Static Context-Aware Articulatory Targets.

The aim of this work is to develop an algorithm for controlling the articulators (the jaw, the tongue, the lips, the velum, the larynx and the epiglottis) to produce given speech sounds, syllables and phrases. This control has to take into account coarticulation and be flexible enough to be able to vary strategies for speech production. The data for the algorithm are 97 static MRI images capturing the articulation of French vowels and blocked consonant-vowel syllables. The results of this synthesis are evaluated visually, acoustically and perceptually, and the problems encountered are broken down by their origin: the dataset, its modeling, the algorithm for managing the vocal tract shapes, their translation to the area functions, and the acoustic simulation. We conclude that, among our test examples, the articulatory strategies for vowels and stops are most correct, followed by those of nasals and fricatives. Improving timing strategies with dynamic data is suggested as an avenue for future work.