基于稀疏表示的NMF抗混响方法

Research on anti-reverberation method of NMF based on sparse representation

在浅海环境中,由于受到混响的影响,主动声呐接收到的信号混淆不清。针对上述问题,提出一种基于稀疏表示的非负矩阵分解(non-negative matrix factorization,NMF)抗混响方法。利用稀疏表示方法处理主动声呐回波信号,然后根据信号的稀疏性,构建基于非负矩阵分解的Kullback-Leibler(KL)问题,通过梯度下降法给出迭代规则,进而得到了目标信号矩阵中的协方差估计。仿真结果表明,相对其他去混响方法,该方法能够有效抑制混响,提高对水下目标的识别率。

In the shallow sea environment,due to the influence of the reverberation,the signal received by the active sound was confusing.In response to the above issues,the article proposes a method of non-negative matrix decomposition based on sparsely expressed sparse expressions(NMF).The above method uses the sparse representation method to process the active sound echo signal,and then builds the Kullback-Leibler(KL)problem based on the sparseness of the signal.The collaborative difference estimation in the signal matrix.The simulation results show that relative to other reverberation methods,this method can effectively suppress the reverberation and improve the recognition rate of underwater targets.