Trainable Videorealistic Speech Animation

I describe how to create with machine learning techniques a generative, video realistic, speech animation module. A human subject is first recorded using a video camera as heshe utters a pre-determined speech corpus. After processing the corpus automatically, a visual speech module is learned from the data that is capable of synthesizing the human subjects mouth littering entirely novel utterances that were not recorded in the original video. The synthesized utterance is re-composited onto a background sequence which contains natural head and eye movement. The final output is video- realistic in the sense that it looks like a video camera recording of the subject. At run time, the input to the system can be either real audio sequences or synthetic audio produced by a text-to-speech system, as long as they have been phonetically aligned.