摘要
文章采用了一种基于三参数组合的方法对语音信号进行清/浊音判决。在传统两参数(短时能量和过零率)算法的基础上增加了自相关函数作为判决参数,减少了清/浊音信号的误判率。经计算机仿真表明,算法切实可行,且算法误判概率小。
The design adopts a three parameters pair , which decisions the voiced/unvoiced in speech signal. It is based on the traditional two parameters pair of voiced/unvoiced decision. The result of simulations on computer shows that this method is more efficient, and the result is more accuracy.
出处
《电脑与信息技术》
2010年第1期33-34,共2页
Computer and Information Technology
关键词
清/浊音判决
短时过零率
短时能量
短时自相关函数
voiced/unvoiced decision
short-time zero-crossing rate
short-time energy
short-time autocorrelation
