Identication of Independent Kinematic Regions of the Face during Speech Production
Jorge Carlos Lucero, Kevin G. Munhall · 2008
This paper reports our progress on the empirical modeling of facial biomechanics during speech pro- duction. Our model is based on decomposing the fa- cial surface into anite set of linearly independent kinematic regions, which is used as a basis to rep- resent the total facial motion. The main algorithm, based on the column-pivoted QR factorization, is re- viewed and compared to other techniques commonly used in statistical regression. The results show that the former technique is more robust to variations in the speech data, and detects regions with a higher measure of independency.