VASA, a framework for generating lifelike talking faces of virtual characters with appealing visual affective skills (VAS), given a single static image and a speech audio clip.
Source: VASA-1 – Microsoft Research
A searchable collection of notes
VASA, a framework for generating lifelike talking faces of virtual characters with appealing visual affective skills (VAS), given a single static image and a speech audio clip.
Source: VASA-1 – Microsoft Research