摘要
通过建立步长因子μ与误差信号е之间的非线性关系,提出一种改进的变步长LMS算法,并将其应用于通信降噪。该算法除了具有传统固定步长LMS算法计算量小、稳定性好、简单、易于实时处理等优点外,理论分析及计算机仿真结果表明,其收敛速度及稳定性优于SVSLMS算法,且不需要进行指数运算,计算复杂度低于SVSLMS算法,用于通信降噪取得了较好的效果。
An improved variable step size adaptive filtering algorithm is presented by building a nonlinear function relationship between μ and error signale,and it is applied to the noise cancelling system of communication.The algorithm is simple and easy to be implemented.Theoretical analysis and computer simulation show that the properties of the algorithm such as convergence speed,steady state error are better than those of SVSLMS algorithm.And it obtains good results in the noise cancelling system of communication.
出处
《噪声与振动控制》
CSCD
北大核心
2007年第4期110-111,共2页
Noise and Vibration Control
关键词
声学
LMS算法
变步长
自适应滤波
噪声抵消
acoustics
LMS algorithm
variable step size
adaptive filtering
noise cancelling
