语音信号同伦非线性模型分析理论与算法  

HOMOTOPY NONLINEAR MODELING FOR SPEECH SIGNALS

作　　者：韦岗[1] 张丽清[1] 李向武[1] 欧阳景正[1] 

机构地区：[1]华南理工大学无线电与自控研究所

出　　处：《自动化学报》1997年第2期201-206,共6页Acta Automatica Sinica

基　　金：国家自然科学基金;国家教委博士点基金;广东省自然科学基金

摘　　要：提出了一种基于同伦理论的语言信号非线性模型分析理论与算法，具有计算量小、稳定性强、收敛性好等一般非线性模型分析方法所没有的优点，同时保持了线性模型的简单性与通用性．Based on the homotopy theory, this paper presents a novel nonlinear modeling method for speech signals, the homotopy nonlinear modeling method (HNMM). Unlike the ordinary nonlinear modeling methods, the HNMM is robust and easy to compute, and has very good convergence property. Besides, the HNMM is nearly as simple as the traditional linear modeling methods and thus can be used very extensively. The validity of the HNMM has been proved by experimental results.

关 键 词：语音信号 建模 非线性模型 算法 

分 类 号：TN912.3[电子电信—通信与信息系统]