Being adept at using Photoshop is so last year, unless you’re using it to put a CNN logo on a wrestler’s face, but now we’re talking about something that could be the future of fake news.

You can thank a research team at the University of Washington for this audiovisual wizardry, where they’ve come up with “a new tool that takes audio files, converts them into realistic mouth movements, and then grafts those movements onto existing video”.

I know that sounds rather confusing, but this video should do the trick. Here’s The Verge:

You can see two side-by-side clips of Barack Obama. The one on the left is the source for the audio, and the one on the right is from a completely different speech, with the researchers’ algorithms use to graft new mouth shapes onto the footage. The resulting video isn’t perfect (Obama’s mouth movements are a little blurry — a common problem with AI-generated imagery) but overall it’s pretty convincing.

See for yourself:

You can bet that would spread like wildfire on social media and Fox News.

Why use Obama?

The researchers said they used Obama as a test subject for this work because high-quality video footage of the former president is plentiful, which makes training the neural networks easier. Seventeen hours of footage were needed as data to track and replicate his mouth movements, researcher Ira Kemelmacher told The Verge over email, but in future this training constraint could be reduced to just an hour.

Researchers hope to use the technology to improve video chat tools like those on Skype calls, making it easier for the video element to function using only someone’s voice.

Great, now you can’t even get out of the tedious business Skype video call with that ‘dodgy connection’ excuse.

If you want a more detailed look at how they did it then consider it done:

[source:theverge]