PROJECT TITLE :
Animating Lip-Sync Characters With Dominated Animeme Models
Character speech animation is historically thought-about as important but tedious work, particularly when taking lip synchronization (lip-sync) into consideration. Although there are some methods proposed to ease the burden on artists to form facial and speech animation, almost none is fast and economical. In this paper, we introduce a framework for synthesizing lip-sync character speech animation in real time from a given speech sequence and its corresponding texts, beginning from coaching dominated animeme models (DAMs) for each quite phoneme by learning the character's animation management signal through an expectation—maximization (EM)-vogue optimization approach. The DAMs are further decomposed to polynomial-fitted animeme models and corresponding dominance functions while taking coarticulation into consideration. Finally, given a novel speech sequence and its corresponding texts, the animation control signal of the character can be synthesized in real time with the trained DAMs. The synthesized lip-sync animation can even preserve exaggerated characteristics of the character's facial geometry. Moreover, since our methodology will perform in real time, it can be used for many applications, such as lip-sync animation prototyping, multilingual animation replica, avatar speech, and mass animation production. Furthermore, the synthesized animation management signal will be imported into three-D packages for further adjustment, therefore our method will be easily integrated into the present production pipeline.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here