The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
Bookmark and Share
Speech Endpoint Detection Algorithm Analyses Based on Short-term Energy
Author(s): 
Pages: 52-54,59
Year: Issue:  7
Journal: AUDIO ENGINEERING

Keyword:  端点检测短时能量边沿检测滤波三态转换判决机制;
Abstract: 研究了噪声环境下,利用短时能量为特征进行语音端点检测的问题.在采用短时全带能量为特征的基础上,提出的算法将短时高频能量作为辅助特征,同时使用了最优边沿检测滤波以及双门限-三态转换判决机制,从而保证了算法在噪声环境下的端点检测准确性和对信号绝对幅度变化的稳健性.实验结果表明,与传统的能量阈值法以及G.729中使用的VAD算法相比,提出的算法在噪声环境下具有更好的性能,是一个简单、高效和稳健的语音端点检测算法.
Related Articles
No related articles found