PROJECT TITLE :

A Practical Model for Live Speech-Driven Lip-Sync

ABSTRACT:

This article introduces a easy, economical, however practical phoneme-primarily based approach to come up with realistic speech animation in real time based mostly on live speech input. Specifically, the authors 1st decompose lower-face movements into low-dimensional principal element spaces. Then, in each of the retained principal component spaces, they choose the AnimPho with the best priority value and therefore the minimum smoothness energy. Finally, they apply motion blending and interpolation techniques to compute final animation frames for the currently inputted phoneme. Through several experiments and comparisons, the authors demonstrate the realism of synthesized speech animation by their approach furthermore its real-time potency on an off-the-shelf computer.