AI Creates Fake Obama via @gnat @ieee

In the new study, the neural net learned what mouth shapes were linked to various sounds. The researchers took audio clips and dubbed them over the original sound files of a video. They next took mouth shapes that matched the new audio clips and grafted and blended them onto the video. Essentially, the researchers synthesized videos where Obama lip-synched words he said up to decades beforehand.

Sourced through Scoop.it from: spectrum.ieee.org

WHY THIS IS IMPORTANT

Fake news is difficult to debunk because we are trained to believe what we read has been vetted and checked for validity. Images and videos are even worse because, until now, it was difficult to alter them in any meaningful way. Technologies like this may change that forever. Watch out for elections 202 in the USA.

Farid Mheir
farid@mheir.com
No Comments

Sorry, the comment form is closed at this time.