[gtranslate]
News

The world gets a little scarier as researchers perfect a way to put words in Obama’s mouth

Using machine learning amongst other techniques, researchers from the University of Washington have successfully created new clips of sorely missed POTUS Barack Obama using audio from old speeches.

In simpler terms, they’re putting words in his mouth. His words, to be fair, but the technology points into pretty uneasy territory. It’s a young Carrie Fischer imposed into Star Wars: Rogue One but way, way freakier.

obama speech machine learning

Using machine learning and freely available footage, researchers have successfully generated new footage of Obama speaking from the White House.

At the moment, the program works by taking audio files of a person speaking and then converting them into realistic mouth shapes that are subsequently grafted onto the head of that person in a pre-existing video.

The algorithm uses machine learning from video already taken of a person to learn how they move their lips and other facial expressions in order to create as perfect a lip sync as is possible. – IFLScience.

Watch a few clips of the technology in action below.