It’s not easy to tell that the Barack Obama in this video is a digital fake, but it is. It was created by researchers at the University of Washington. They developed an AI model of the former president’s mouth movements so that the bot’s lips sync up to any audio track. In this video, the digital Mr. Obama says things that the carbon-based Obama never said.
From the YouTube description:
Given audio of President Barack Obama, we 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. Given the mouth shape at each time instant, we synthesize high quality mouth texture, and composite it with proper 3D pose matching to change what he appears to be saying in a target video to match the input audio track.
The researchers say that even though the video looks real, it’s easy to reverse engineer it and find out it’s a fake. But will this always be the case?