一种自适应样本熵的语音端点检测方法

Adaptive Sample Entropy of Speech Endpoint Detection

提出了一种新型基于自适应样本熵的语音端点检测算法。为了提高语音信号端点检测的准确率,采用了样本熵和过零率相互结合的方法,通过一个可调参数对阈值H进行自适应调整得到合理的门限值来获得良好的检测效果。在Matlab中进行试验仿真,其仿真结果证明在信噪比下降到0以后,基于自适应样本熵的方法检测正确率仍可达到90%,其检测性能完全符合设计要求,且优于传统基于能量的方法。

A new speech endpoint detection algorithm based on adaptive sample entropy is proposed. The sample entropy combine with zero crossing ratemethodin is used in order to improve the detection accuracy, good detection effect is obtained through an adjustable parameters of the threshold H. Simulation in MATLAB, the results show that when the signal - to - noise ratio dropped to zero, the method based on adaptive sample entropy detection accuracy can still reach 90% , the detec- tion performance fully meet the design requirements, and is superior to the traditional method based on energy.