基于双路径特征融合网络的背景信号抑制算法

打开文本图片集

中图分类号：TN971 文献标志码：A DOI：10.12305/j.issn. 1001-506X.2025.07. 33

Abstract： Itis vital for thedetection of critical and important signals to suppress background signals at the end of receiver effectively.Curent methods inadequatelyutilizesignal context information，renderingitchallnging toaddress the issueof background signal suppression of single channel in noisy environments and time-frequencyoverlaps.To regard this，a dual-path feature fusion mask-based suppresson （DPFF-MS）algorithm is proposed，utilizing midfrequency time-domain signals. The algorithm utilizes a neural network to fit the mask suppresion model， effectively suppressing background signals. The high-dimensional transformation and inverse transformation of signalscan be enabled by the employment of a suite of convolutional encoder-decoder networks，diminishing the adverse effects of noise. A dual-path feature fusion （DPFF） module is developed，which leverages long shortterm memory（LSTM） networks of varying paths to alternately extract both local features and global contextual information.An iterative attention feature fusion （iAFF） is used to optimize the process of fusing features of different scales，fully exploiting the intra-pulse and inter-pulse information to address the suppresson issue in time-frequency overlapping environments.The experimental results indicate that，in comparison to other signal processing approaches and neural network models，the proposed model shows significant enhancements in terms of scaleinvariant source-to-noise ratio（SI-SNR）and background pulse suppresson rate.Furthermore，it significantly reduces the number of model parameters，making it straightforward to deploy and possess high application value.

Keywords： electronic reconnaissance; suppresion of background signal;； deep learning;； multi-scale feature fusion

0 引言

背景信号抑制是指减弱或消除混叠在关重信号中的背景辐射源信号。（剩余15439字）