|Title||Autonomous Speaker Agent|
|Publication Type||Conference Paper|
|Year of Publication||2004|
|Authors||Smid, K, Pandzic, IS, Radman, V|
|Conference Name||Computer Animation and Social Agents CASA 2004|
|Conference Location||Geneva, Switzerland|
Autonomous Speaker Agent is a graphically embodied animated agent (a virtual character) capable of reading plain English text and rendering it in a form of speech, accompanied by the appropriate, natural-looking facial gestures. The system uses lexical analysis and statistical models of facial gestures in order to generate the gestures related to the spoken text. It is intended for the automatic creation of the realistically animated virtual speakers, such as newscasters and storytellers, and incorporates the characteristics of such speakers captured from the training video clips. Autonomous Speaker Agent is based on a visual text-to-speech system which generates lip movement synchronized with the generated speech. This is extended to include eye blinks, head and eyebrow motion, and a simple gaze following behavior. The result is a full face animation produced automatically from the plain English text.