Extending Visual Speech Synthesis for Polish with basic emotion model
Abstract: Expressing emotions is a very important feature of Visual Speech Synthesis systems. In 1972 the first “basic emotions” list was introduced, by Paul Ekman. Since then few different classifications were published. Most famous “basic emotion” models are briefly described in this paper. In previous publication new Visual Speech Synthesis system for Polish was presented. The system was based on Xface toolkit and “Karol” face model. The aim of this paper is to add “basic emotion” model, according to Paul Ekman’s classification, into “Karol” face model. To achieve this goal new emotional keyframes were proposed. This new functionality of “Karol” face model, allows to generate talking human face animations, which express emotions. The subjective test of new functionality are also included in the paper. The results showed that more information about speakers emotions is read from human face expression than form human speech signal. People can more easily recognize speakers emotion when they see his face expression.
Keywords: Visual Speech Synthesis, emotion, Xface, Ekman
Area: Electronics and Information Technologies
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.