雷达辐射源音频信号声纹识别方法  

Voiceprint Recognition of Radar Emitter Audio Signal

作　　者：聂晓华[1] 周庆军[1] 王毅[1] 李徽 

机构地区：[1]江苏自动化研究所,江苏连云港222006

出　　处：《探测与控制学报》2009年第3期9-13,共5页Journal of Detection & Control

基　　金：国家973重点基础研究发展规划项目资助(2007CB61364)

摘　　要：针对复杂的电磁环境中,雷达辐射源音频信号人工识别方法存在耗时长、误判和错判等问题,提出一种利用声纹识别和计算机技术对雷达辐射源音频进行识别的方法.利用了声纹识别关键技术——美尔倒谱系数特征提取和动态时间规整算法实现雷达辐射源音频自动识别,实验结果表明:该方法缩短了识别时间,提高了识别的正确率。In complex electromagnetic environment, manual recognition of radar emitter audio signal is time-consuming and suffers misjudgment problems. In this paper, a novel approach based on voiceprint recognition and computer technology is proposed for radar emitter audio signal recognition which takes advantage of Mel frequency cepstral coefficient and the dynamic time warping which are the key technologies in voiceprint recognition. The experiment results show that with this approach the recognition time is shortened and the identification rate is improved.

关 键 词：雷达辐射源 音频信号 声纹识别 MFCC DTW 

分 类 号：TN391.4[电子电信—物理电子学]