Speech-driven portrait animation generation models have made significant progress in generating realistic and dynamic portrait animations. The class of end-to-end latent diffusion paradigms ...

Audio-driven talking-head video generation is a critical task in cross-modal expressive synthesis, with applications in virtual humans, digital content creation, and human-computer interaction.

I was present at the audio mixing stage of Aardman Animations' "The Wrong Trousers" or "Wallace and Gromit" as most people remember it. This stop-motion animation classic was hilarious from the first ...