Cao, YongFaloutsos, PetrosPighin, FrédéricD. Breen and M. Lin2014-01-292014-01-2920031-58113-659-51727-5288https://doi.org/10.2312/SCA03/225-231We present a new method for editing speech related facial motions. Our method uses an unsupervised learning technique, Independent Component Analysis (ICA), to extract a set of meaningful parameters without any annotation of the data. With ICA, we are able to solve a blind source separation problem and describe the original data as a linear combination of two sources. One source captures content (speech) and the other captures style (emotion). By manipulating the independent components we can edit the motions in intuitive ways.