ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,784,318, issued on Nov. 3, was assigned to Amazon Technologies Inc. (Seattle).
"Techniques for generating scalable talking avatars" was invented by Urwa Muaz (London), Brandon Michael Smith (Fremont, Calif.), Baris Gecer (London), Ganesh Subramanian Iyer (Cupertino, Calif.) and Nicolas Heron (New York).
According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques are disclosed for generating realistic talking avatar videos from a prompt and a script. A computer system can implement a trained avatar model that includes a diffusion model that can generate a neural texture usable to generate each frame of a talking avatar video. The computer system can generate ...