一种组合参数的语音信号清/浊音判决方法

A Simple Method of Unvoiced/Voiced Classification of Speech Signal

提出一种基于组合参量的语音信号清 /浊判决方法 ,减小了清 /浊单信号特征概率分布的重叠区域 ,程序设计简练。经计算机仿真表明 ,与单一参量判决方法相比 ,其错判率小 ,抗噪性好。

This paper presents a simple method of unvoiced/voiced classification based on combinatorial parameters, which decreases the overlap area of the characteristic probability density of the unvoiced/voiced speech signals. Simulations on computer show that the method is more efficient and robust than that of classification based on single parameter, and the design of the program is simple and concise.