Fake Obama Created By AI Is A Reminder of How Technology Is Only Evolving

You heard me right, this summer a team of computer scientists from University of Washington made a video of Obama … without the stress of finding and asking for a video Obama. How did they do this? By synthesizing everything from Obama’s mouth texture and a 3D composite, allowing their video’s audio to match with movements pulled from 14 hours of actual Obama stock footage they collected. The results are astonishing.

We show that by training on a large amount of video of the same person, and designing algorithms with the goal of photorealism in mind, we can create believable video from audio with convincing lip sync. Œis work opens up a number of interesting future directions, some of which we describe below.

The team says that literally anyone’s cadence including the way that they speak, and interact can be studied then replicated. The synthetic Obama project involved neural network AI to get his mouth just right then later matching with the footage they collected in order to get … yup, the closest thing to President Obama you could imagine.

Now they can literally take any Obama audio and reverse engineer it with AI.

The scientists say that as technology remains a part of our future, it can be used negatively and positively. This study is a perfect example of the power of technology and using its inevitable growth. Pretty soon it will be very difficult to tell the difference between what’s real and what’s fake.

Zentist is tackling future tech by establishing core principles with an advanced dental image recognition system — a thoughtful, ethical, technologically advanced that can benefit both dentists and patients. That’s right — pretty soon you won’t have to search for Dental Implants or dental care near you. With Zentist’s platform, we’re making dental care smarter than ever by matching patients, accurate machine diagnostics, and affordability. Want to learn more? Visit Zentist.io.