计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (18): 141-143.

• 数据库、信号与信息处理 • 上一篇    下一篇

基于混沌系统模型的非线性语音预测器

覃爱娜1,黄 仲1,2,桂卫华1   

  1. 1.中南大学 信息科学与工程学院,长沙 410083
    2.株洲师范高等专科学校 物理与电子工程系,湖南 株洲 412007
  • 收稿日期:2007-12-10 修回日期:2008-03-10 出版日期:2008-06-21 发布日期:2008-06-21
  • 通讯作者: 覃爱娜

Nonlinear speech predictor using models for chaotic systems

QIN Ai-na1,HUANG Zhong1,2,GUI Wei-hua1   

  1. 1.College of Information Science and Technology,Central South University,Changsha 410083,China
    2.Department of Physics and Electron Engineering,Zhuzhou Teachers’ College,Zhuzhou,Hunan 412007,China
  • Received:2007-12-10 Revised:2008-03-10 Online:2008-06-21 Published:2008-06-21
  • Contact: QIN Ai-na

摘要: 语音信号的产生过程是非线性的,而且具有混沌性。相对于线性模型,在重构相空间中建立的语音信号模型更接近实际系统,神经网络是建立非线性系统模型的常用工具。实验结果表明:在重构相空间中建立的基于径向基函数神经网络的预测器较线性预测器在性能上有明显提高。

Abstract: The speech production is nonlinear and chaotic.Nonlinear models for speech in the reconstructed phase space is more appropriate for the actual systems than the linear one.Artificial neural network has been widely used in modeling the nonlinear systems.The experiment results indicate that the nonlinear predictor based on RBF network is more accurate than the linear predictor.