ニューロベビー : 音声から感情を認識して反応する表情合成システム : 視聴覚技術

概要

論文の詳細を見る
Neuro-Baby is a totally new type of interactive performance system which responds to human voice with a computer-generated baby face and sound effects. Emotion space model is employed to categorize the feelings of the speaker. To recognize the human voice we used a neural network which has been taught the relationship between a set of digitized wave patterns and the locations of several emotion types in the emotion space. The facial expression is synthesized continuously according to the location which the neural network generates. Flexible design of Neuro-Baby is possible by changing the face design, the layout in the emotion space, sensitivity to the transition of the feelings or the teaching pattern for the neural network.
社団法人映像情報メディア学会の論文
1992-06-23