Researchers Have Figured Out How To Fake News Video With AI (qz.com)

An anonymous reader quotes a report from Quartz: A team of computer scientists at the University of Washington have used artificial intelligence to render visually convincing videos of Barack Obama saying things he's said before, but in a totally new context. In a paper published this month, the researchers explained their methodology: Using a neural network trained on 17 hours of footage of the former U.S. president's weekly addresses, they were able to generate mouth shapes from arbitrary audio clips of Obama's voice. The shapes were then textured to photorealistic quality and overlaid onto Obama's face in a different "target" video. Finally, the researchers retimed the target video to move Obama's body naturally to the rhythm of the new audio track. In their paper, the researchers pointed to several practical applications of being able to generate high quality video from audio, including helping hearing-impaired people lip-read audio during a phone call or creating realistic digital characters in the film and gaming industries. But the more disturbing consequence of such a technology is its potential to proliferate video-based fake news. Though the researchers used only real audio for the study, they were able to skip and reorder Obama's sentences seamlessly and even use audio from an Obama impersonator to achieve near-perfect results. The rapid advancement of voice-synthesis software also provides easy, off-the-shelf solutions for compelling, falsified audio. You can view the demo here: "Synthesizing Obama: Learning Lib Sync from Audio"

Comments

It'll convince people who want to be convinced

[rsilvergun]

and that's the point. There's millions of folks out there itching for an excuse to do what they already want to do. Fake news doesn't work on people thinking critically, but you're not after those.

Re:It'll convince people who want to be convinced

[Mashiki]

Fake news doesn't work on people thinking critically, but you're not after those.

Not true in the least. Remember when Dateline used model rocket boosters to blow up the gas tanks on pickup trucks? You know their target audience for that show at the time was 30-45 college educated or higher. Fake news works well on anyone who's ideologically deep in a rabbit hole and wants to engage in confirmation bias.

Let's look at two cases over the last 3 years: Gamergate, where the FBI could find no incidences of harassment from anyone tied to it. Demographics educated at college level or higher, married, has family, has high disposable income, roughly 15% are female, has a significant minority quotient from all over the world to boot and aligns politically left. But the media continues on with the lie that they're harassers who pump out death threats, are worse then isis, and then scrub away those women and minorities because they don't fit the narrative(that is if the anti-gg people simply don't call them house n*iggers, or uncle toms). The media view of the people in Gamergate are: single, white, males who live in their parents basement or are virgins living alone. Nice fabrications huh?

Or you can take a look at the "Trump-Russia-Collusion" story. Which has evolved from "Russia colluded with Trump" to "his son talked with a lawyer who's visa expired that the Obama administration specifically let back in at the behest of Susan Rice" along with "Putin talked with Trump during dinner." But the entire thing has fallen apart to the point where pundits outside of the main of the party are saying "shut-up, this is hurting us more then helping." If the media has one narrative, it's very easy to see from the outside. But it sure is self-reinforcing if you're in that rabbit hole.

Lipreader says no.

[mykro76]

I'm deaf and have been lipreading for more than 40 years. I can confirm these videos are not lip-readable - many words are only half formed (one syllable where there should be two) and the mouth transitions are too jerky. It's a good attempt and I'm positive the tech will just keep getting better, but right now, it's not there yet.

They call this news??

[FrankHaynes]

I've seen recent news broadcasts and the only thing that would mimic them successfully would be Artificial Stupidity.

Autist says no.

[Anonymous Coward]

Being on the autism spectrum, I have a tendency to focus on peoples' mouths when they speak. I would characterize the quality of the generated content as abysmal.

One of the major giveaways is that phonemes which involve the lips interacting with teeth are way off. Just not even close. The word "visited" looks for all the world like what's being said is "dizited". How can they generate a 'd' motion for a 'v' sound and still have the balls to publish their paper, let alone make any sort of claims that it's believable? It's absolutely galling, precisely because it's only accurate enough to fool people who want to be fooled, leaving those of us who know better shouting weakly from the proverbial back of the room.