Naslov
Automatic Content Production for an Autonomous Speaker Agent

Autori
Šmid, Karlo ; Radman, Viktorija ; Pandžić, Igor

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Conversational Informatics for Supporting Social Intelligence and Interaction: Situational and Environmental Information Enforcing Involvement in Conversation / Nakano, Yukiko I. ; Nishida, Toyoaki - Hartfield : AISB, The Society for the Study of Artificial Intelligence and the Simulation of Behaviour, 2005, 103-113

Skup
AISB 2005 Convention: Social Intelligence and Interaction in Animals, Robots and Agents

Mjesto i datum
Hatfield, Ujedinjeno Kraljevstvo, 12.04.2005. - 15.04.2005

Vrsta sudjelovanja
Pozvano predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
animated agent; facial gestures; lexical analysis; statistical models; visual text-to-speech

Sažetak
We present a graphically embodied animated agent (a virtual speaker) capable of reading plain Eng-lish text and rendering it in a form of speech accompanied by the appropriate facial gestures. Our system uses a lexical analysis of an English text and statistical models of facial gestures in order to automatically generate the gestures related to the spoken text. It is intended for the automatic crea-tion of the realistically animated virtual speakers, such as newscasters and storytellers and incorpo-rates the characteristics of such speakers captured from the training video clips. Our system is based on a visual text-to-speech system which generates a lip movement synchronized with the generated speech. This is extended to include eye blinks, head and eyebrow motion, and a simple gaze follow-ing behavior. The result is a full face animation produced automatically from the plain English text.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo

POVEZANOST RADA