基于雷达信号转换的多维空间声音识别技术  

Multidimensional Spatial Sound Recognition Technology Based on Radar Signal Conversion

作　　者：孟东 MENG Dong(The 3rd Research Institute of China Electronics Technology Group Corporation,Beijing 100015,China)

机构地区：[1]中国电子科技集团公司第三研究所,北京100015

出　　处：《电声技术》2024年第6期150-152,156,共4页Audio Engineering

摘　　要：为增加雷达信号的识别方式,提出一种基于雷达信号转换的多维空间声音识别技术。首先,将脉冲式的雷达信号拼接为连续特征声音信号;其次,使用高斯混合模型(Gaussian Mixed Model,GMM)训练拼接后的声信号;再次,根据GMM准则将未知雷达目标转化为特征向量,并与已训练的多维特征向量做对比,得到未知声目标的最大输出概率类型;最后,进行实验分析。实验结果表明,采用基于雷达信号转换的多维空间声音识别技术可以有效识别不同类型的雷达目标,为识别雷达信号提供了一种特殊的识别特征。To increase the recognition methods of radar signals,a multi-dimensional spatial sound recognition technology based on radar signal conversion is proposed.Firstly,concatenate the pulse type radar signals into continuous feature sound signals.Secondly,use Gaussian Mixed Model(GMM)to train the concatenated sound signal.Thirdly,according to the GMM criterion,the unknown radar target is transformed into a feature vector,and compared with the trained multidimensional feature vector to obtain the maximum output probability type of the unknown acoustic target.Finally,conduct experimental analysis.The experimental results show that using multi-dimensional spatial sound recognition technology based on radar signal conversion can effectively identify different types of radar targets,providing a special recognition feature for identifying radar signals.

关 键 词：雷达目标识别 声目标识别 多维特征空间 

分 类 号：TN957.51[电子电信—信号与信息处理]