Articulatory speech synthesis is a technique used to generate speech by replicating the movements of human articulators such as lips, tongue, glottis, and the vocal tract. This approach is, sometimes, considered to be the most authentic way of synthesizing speech since it mimics the process used by humans. Nevertheless, implementing this technique can be quite challenging due to difficulties in modeling articulator behaviors. For instance, it can be tough to gather data necessary for articulator simulation. Speech quality produced by articulatory synthesis is generally inferior compared to other speech synthesis techniques. ![[tsukanova-2018-superimposed.png|400]] [Tsukanova et al. (2018)](https://hal.science/hal-01937950/document#:~:text=Articulatory%20speech%20synthesis%20is%20a,incorporate%20any%20articu%2D%20latory%20information.) ## References Cecil H Coker. A model of articulatory dynamics and control. Proceedings of the IEEE, 64(4): 452–460, 1976. Christine H Shadle and Robert I Damper. Prospects for articulatory synthesis: A position paper. In 4th ISCA Tutorial and Research Workshop (ITRW) on Speech Synthesis, 2001 Anastasiia Tsukanova, Benjamin Elie, Yves Laprie. Articulatory Speech Synthesis from Static Context-Aware Articulatory Targets. Qiang Fang; Jianwu Dang; Pascal Perrier; Jianguo Wei; Long- biao Wang; Nan Yan. Studies on Speech Production, 10733, Springer, pp.37-47, 2018, Lecture Notes in Computer Science, 978-3-030-00125-4. 10.1007/978-3-030-00126-1_4 . hal-01937950, 2018