Automatic synthesis of facial expression with speech

In this paper, a method of synthesizing speech facial expression by the Kohonen's artificial neural networks (KNN) is proposed The proposed method generates facial expression series in speech of vowel to vowel with KNN automatically, which uses the stiff images of the five Japanese vowels pronunciation and non-speech state. Synchronization with speech sound was done by separating the stable sections and transition sections of facial expression based on the sound power. assigning a fixed facial expression to the stable section and the evenly distributed facial expression series to the transition section. The proposed method yielded much realistic speech facial expression.