一种用于枪声的多级检测识别技术  

A multi-level detection and identification technique for gunshots

作　　者：张涛[1] 苏春玲[1] 

机构地区：[1]天津大学电子信息工程学院,天津300072

出　　处：《电子设计工程》2013年第18期56-58,61,共4页Electronic Design Engineering

摘　　要：声音无处不在,声音的检测与识别一直是声音研究领域的重要内容。其中公共场所环境中的突发声音的检测一直是一个难题,本文提出了一种利用短时能量和短时平均过量率以及MFCC和DTW对枪声等特定声音的多级检测算法。实验结果表明,本算法具有较低的计算复杂度,易于实现,而且检测的漏检率和误检率都很理想。As we known, the sound is everywhere. The detection and recognition of the sound has been an important content of the sound＇s research. It has been a problem that the detection of a burst of sound in the environment of the public places. This paper proposes a multi-stage way to detect gun shots. This way takes advantage of short-term energy and short-time average zero crossing rates and MFCC and DTW. The experiments show that this method has low computation complexity, and can be implemented easily. From the results, we can also find that ideal undetected rates and false detection rates can be obtained.

关 键 词：枪声 短时能量 短时过零率 MFCC DTW 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]