作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (17): 237-238,. doi: 10.3969/j.issn.1000-3428.2007.17.081

• 多媒体技术及应用 • 上一篇    下一篇

语音驱动唇形自动合成算法

林 鑫1,陈 桦2,王开志3,王继成1   

  1. (1. 同济大学计算机系,上海 200092;2. 上海交通大学计算机系,上海 200240;3. 摩托罗拉中国研究中心,上海 200041)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-09-05 发布日期:2007-09-05

Automatic Lip Synchronization Algorithm Driven by Speech

LIN Xin1, CHEN Hua2, WANG Kai-zhi3, WANG Ji-cheng1   

  1. (1. Dept. of Computer Science, Tongji University, Shanghai 200092; 2. Dept. of Computer Science, Shanghai Jiaotong University, Shanghai 200240; 3. Motorola China Research Center, Shanghai 200041)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-09-05 Published:2007-09-05

摘要: 定义了10种基本的嘴形。以Mel频率倒谱系数(MFCC)作为语音特征,通过SVM分类器进行元音a,i,u的识别,根据其对应量化后的语音能量,映射到嘴形序列,进行中值滤波和排除“奇异点”。该算法在基于语音驱动人脸动画系统中的应用取得了良好的效果。

关键词: 语音, 嘴形, Mel频率倒谱系数, 能量

Abstract: This paper defines 10 kinds of mouth shapes. The MFCC feature of speech is extracted to recognize vowel (a, i, u) through SVM classifier. According to corresponding quantified speech energy, the speech is mapped to mouth shapes sequences, and median algorithm filter and “odd point” eliminating are undertaken. The algorithm has been applied to the system of face animation driven by speech and achieves good results.

Key words: speech, mouth shape, MFCC, energy

中图分类号: