摘要
通过试验对影响算法收敛性的参数进行研究,合理选取参数提高自适应预测器的精度。试验对语音信号进行LPC分析得到的AR(2)信号为预测器输入,MATLAB仿真构造自适应线性预测器,采用LMS算法进行训练。试验表明,输入信号特征值的分散度越大,其收敛性越差。自适应预测试验验证了自适应预测过程参数分析选取的有效性。
This paper, through the experiment, studies the parameters influencing the convergence of LMS algorithm, and parameters are selected to improve the precision of adaptive prediction. In the experiment, by making LPC analysis to the sound signal, the AR（2） signal obtained is prediction input; the adaptive linear is structured by MATLAB emulation program and the adaptive prediction is trained by LMS algorithm. The result shows that the bigger the scatter of input signal is, the worse the convergence of adaptive prediction is. According to the outcome, the effectiveness of parameter analysis in the adaptive prediction is confirmed.
出处
《温州职业技术学院学报》
2008年第2期41-43,49,共4页
Journal of Wenzhou Polytechnic
