There is Microsoft Research Asia opened new experimental AI tool Called VASA-1, it can take a still image or drawing of a person and an existing audio file to create a live speaking face from them in real time. It has the ability to create facial expressions and head movements for an existing still image and lip movements to match a speech or song. The researchers have uploaded many samples on the project page, and the results look good enough to trick people into thinking they’re real.
While the lip and head movements in the examples may still look a bit robotic and synchronized upon closer inspection, it’s still clear that the technology can be abused to easily and quickly create deep fake videos of real people. The researchers themselves are aware of this potential and have decided not to release “an online demo, API, product, additional application details, or related offerings” until they are confident their technology will be “used responsibly and appropriately.” rules”. However, they did not say whether they plan to implement certain safeguards to prevent bad actors from using them for nefarious purposes, such as creating deep fake porn or disinformation campaigns.
The researchers believe that their technology has many benefits, despite the potential for abuse. They said it could be used to increase equity in education, as well as improve accessibility for those with communication difficulties, perhaps by giving them access to an avatar that can communicate. It could also provide companionship and therapeutic support for those in need, they said, adding that VASA-1 could be used in applications that offer access to AI characters that humans can speak to.
according to paper announced VASA-1 was trained on the VoxCeleb2 Dataset, which contains “over 1 million expressions for 6,112 celebrities” extracted from YouTube videos. Although the tool was trained on real faces, it also works on artistic photos, such as the Mona Lisa, which the researchers playfully combined with an audio file of Anne Hathaway’s viral performance by Lil Wayne. Paparazzi. It’s so delicious that it’s worth a look, even if you doubt what such technology is capable of.
This article contains affiliate links; we may earn a commission if you click on such a link and make a purchase.