engleski

Simulation of a television speaker with natural face gestures

Autonomous Speaker Agent is a graphically embodied animated agent (a virtual character) capable of reading plain English text and rendering it in form of speech accompanied by appropriate, natural-looking facial gestures. The system uses lexical analysis and statistical models of facial gestures in order to generate gestures related to spoken text. It is intended for automatic creation of realistically animated virtual speakers, such as newscasters and storytellers, and incorporates the characteristics of such speakers captured from training video clips. Autonomous Speaker Agent is based on a visual text-to-speech system which generates lip movement synchronized with generated speech. This is extended to include eye blinks, head and eyebrow motion, and a simple gaze following behaviour. The result is full face animation produced automatically from plain English text.

facial animation; virtual character; visual text-to-speech; MPEG-4 FBA; embodied

nije evidentirano