计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (9): 36-39.

• 学术探讨 • 上一篇    下一篇

人脸动画中语音可视化算法研究进展

周东生 张强 魏小鹏   

  1. 大连大学 大连大学 大连大学校长办公室
  • 收稿日期:2006-07-26 修回日期:1900-01-01 出版日期:2007-03-21 发布日期:2007-03-21
  • 通讯作者: 张强

Progress in Audio-Visual Conversion Algorithms in Facial Animation

  • Received:2006-07-26 Revised:1900-01-01 Online:2007-03-21 Published:2007-03-21

摘要: 从人脸动画合成技术的发展、特点及应用出发,介绍了五种主要的人脸动画合成技术,重点对语音驱动的人脸动画中矢量量化、高斯混合模型、神经网络、隐马尔可夫等四种语音可视化算法的特点进行了对比分析,展望了语音可视化算法的发展与应用前景。 [关键词]:人脸动画;语音可视化

关键词: 人脸动画, 语音可视化

Abstract: Five main types of synthesized technology of facial animation are introduced from the point of development, characteristics and application of facial animation. Comparison and analysis on the four typical audio-visual conversion algorithms including vector quantization, Gaussian mixture model, neural networks and hidden markov model in speech-driven facial animation are laid emphasis on in this paper. In addition, the development and possible applications are also discussed.

Key words: facial animation, audio-visual conversion algorithms