Realistic Face Animation for a Czech Talking Head

This paper is focused on improving visual Czech speech synthesis. Our aim was the design of a highly natural and realistic talking head with a realistic 3D face model, improved co-articulation, and a realistic model of inner articulatory organs (teeth, the tongue and the palate). Besides very good articulation our aim was also expression of the mimic and emotions of the talking head. The intelligibility was verified by the listening test and the results of this test were analysed. Firstly, the face model reconstruction from real data is presented. A 3D computer vision was employed in order to obtain a model of an arbitrary face. The stereovision technique that is used to reconstruct the model is described in detail in Section 2. Details concerning a visual speech synthesis are discussed in Section 3. Special features of the visual speech synthesis of the Czech language are mentioned, too. Furthermore, the design of a talking head including the solution of co-articulation problem is presented. Next, the modeling of expression and emotions in animation is described. The last part of the paper, Section 4, contains results of the performed listening test.