AI can transform spoken language into photorealistic sign language videos

By Chris Stokel-Walker

Many deaf people use sign language to communicate

FluxFactory / Getty Images

An AI that can create photorealistic videos of sign language interpreters from the language could improve accessibility by eliminating the need for people.

Ben Saunders of the University of Surrey in the UK and his colleagues used a neural network that converts spoken language into sign language. The system called SignGAN then assigns these characters to a 3D model of the human skeleton.

The team also trained the AI ​​in videos of real sign language interpreters, teaching her how to create a photorealistic video of anyone who was based on an image of …