| 基于语音情感识别的多表情人脸动画方法 |
| |
| 引用本文： | 谢金晶,陈益强,刘军发.基于语音情感识别的多表情人脸动画方法[J].计算机辅助设计与图形学学报,2008,20(4):520-525. |
| |
| 作者姓名： | 谢金晶 陈益强 刘军发 |
| |
| 作者单位： | 中国科学院计算技术研究所普适计算研究中心,北京,100190 |
| |
| 基金项目： | 国家自然科学基金
,
北京市科技新星计划基金 |
| |
| 摘 要： | 基于MPEG-4标准，实现了一种由彩铃语音及蕴含情感共同驱动生成人脸动画的方法和系统．选用HMM作为分类器，训练使其识别语音库中嗔怒、欣喜、可爱、无奈和兴奋5类情感，并对每类情感建立一组与之对应的表情人脸动画参数（FAP）．分析语音强弱得到综合表情函数，并用此函数融合表情FAP与唇动FAP，实现人脸表情多源信息合成，得到综合FAP驱动人脸网格生成动画．实验结果表明，彩铃语音情感识别率可达94．44％，该系统生成的人脸动画也具有较高的真实感．
|
| 关 键 词： | MPEG-4标准 语音情感识别 隐马尔可夫模型 人脸动画 |
| 修稿时间： | 2007年9月6日 |
Multi-expression Facial Animation Based on Speech Emotion Recognition |
| |
| Xie Jinjing,Chen Yiqiang,Liu Junfa.Multi-expression Facial Animation Based on Speech Emotion Recognition[J].Journal of Computer-Aided Design & Computer Graphics,2008,20(4):520-525. |
| |
| Authors: | Xie Jinjing Chen Yiqiang Liu Junfa |
| |
| Affiliation: | Xie Jinjing Chen Yiqiang Liu Junfa(Research Center for Pervasive Computing,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190) |
| |
| Abstract: | A facial animation generation system is implemented based on MPEG-4 standard according to both multimedia ring and the emotion embedded. By choosing hidden Markov model as the classifier, five kinds of emotions, including anger, gratulation, cute, puzzle, excitement, are generated in speech database through training, and then a set of expression FAPs for each kind of emotion is built up. By analyzing the intensity of speech signal, synthesis expression function is obtained and used to integrate expression F... |
| |
| Keywords: | MPEG-4 standard speech emotion recognition hidden Markov model facial animation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
