Obama Lip Sync Teaser Video (VIDEO) University of Washington This video is under embargo. Please login to access this video. To view this video please enable JavaScript, and consider upgrading to a web browser that supports HTML5 video Caption A new tool developed by computer vision researchers at the Paul G. Allen School of Computer Science & Engineering at the UW creates realistic videos from audio files alone. Given audio of President Barack Obama speaking, the tool uses machine learning to synthesize a high-quality video of him speaking with accurate lip sync, composited into a target video clip. Trained on many hours of his weekly address footage, a recurrent neural network learns the mapping from raw audio features to mouth shapes. Credit University of Washington Usage Restrictions with credit License Licensed content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.