AVSP 2003 - International Conference on Audio-Visual Speech Processing
September 4-7, 2003
We have designed and implemented a toolkit for real-time animation of virtual 3D talking head, “Artificial Person”. Synchronized auditory and visual speech are automatically produced from input text, which can be enriched by user definable commands to perform specific gestures, as for example head nodding or facial expressions. The toolkit is extensible through external configuration files, so new actions can be quickly added. We have configured the Artificial Person to display facial expressions and phoneme articulations. Modular design of the toolkit allows to easily replace parts of the system or to detach and run them on different computers. Artificial Person can be used to produce controllable stimuli in psychophysical and neurophysiological research on audio-visual perception of speech and emotions.
Bibliographic reference. Frydrych, Michael / Kätsyri, Jari / Dobsík, Martin / Sams, Mikko (2003): "Toolkit for animation of Finnish talking head", In AVSP 2003, 199-204.