All Possible Ways
Member
In another example of crazy machine learning, researchers were able to train a software to generate fake Obama videos, saying stuff he never said (to be clear, all words were actually said by him at some point, in another context), by analyzing his facial movements when saying various words from existing video footage of him.
http://spectrum.ieee.org/tech-talk/robotics/artificial-intelligence/ai-creates-fake-obama
Impressive to say the least. I look forward to the future where you won't be able to trust what was said in any video.
Edit: Here's an 8 minute video that goes in a bit more detail: https://www.youtube.com/watch?v=9Yq67CjDqvw
And the actual paper: http://grail.cs.washington.edu/projects/AudioToObama/siggraph17_obama.pdf
Digitize me if old.
http://spectrum.ieee.org/tech-talk/robotics/artificial-intelligence/ai-creates-fake-obama
Computer scientists at the University of Washington previously revealed they could generate digital doppelgängers of anyone by analyzing images of them collected from the Internet, from celebrities such as Tom Hanks and Arnold Schwarzenegger to public figures such as George W. Bush and Barack Obama. Such work suggested it could one day be relatively easy to create such models of anybody, when there are untold numbers of digital photos of everyone on the Internet.
The researchers chose Obama for their latest work because there were hours of high-definition video of him available online in the public domain. The research team had a neural net analyze millions of frames of video to determine how elements of Obama's face moved as he talked, such as his lips and teeth and wrinkles around his mouth and chin.
Impressive to say the least. I look forward to the future where you won't be able to trust what was said in any video.
Edit: Here's an 8 minute video that goes in a bit more detail: https://www.youtube.com/watch?v=9Yq67CjDqvw
And the actual paper: http://grail.cs.washington.edu/projects/AudioToObama/siggraph17_obama.pdf
Digitize me if old.