We present a method for generating a video of a talking face. The method takes as inputs: (i) one still image of the target face, and (ii) an audio speech segment; and outputs a video of the target face lip synched with the audio. The method works in real time, and at run time, is applicable to previously unseen faces and audio (i.e. not part of the training data). To achieve this we propose an encoder-decoder CNN model that uses a joint embedding of the face and audio to generate synthesised talking face video frames. The model is trained on tens of hours of unlabelled videos. We also show results of re-dubbing videos using speech from a different person.
Captured tweets and retweets: 1