← All terms

Facial Avatar

Also known as: Singing head, Talking head avatar

A digital, animated representation of a face — typically rendered as a 3D or stylized 2D character from the neck up — driven by audio, video, or data signals to produce expressive facial behavior such as lip-sync, emotional expression, gaze, and head motion. In accessibility contexts, facial avatars are used to give d/Deaf and Hard of Hearing audiences visual access to vocal and emotional qualities of speech or music, to supplement captions and sign-language interpretation, and to generate sign-language content at scale. Design considerations include avoiding the uncanny valley through stylization, anchoring motion to real articulatory sources, and involving Deaf communities in co-design to avoid the 'signing avatar as disability dongle' critique.

Category: Deaf accessibility · Multimedia Accessibility · Emerging Technology · User Interface

Related: Music Visualization · Sign Language · Captions · Multimodal Interaction · Deaf and Hard of Hearing

Sources