An Efficient Voice Signal Detection Framework Based on Time-Frequency Feature Fusion and Anchor-Free Detection Mechanism
LI Chunhui
XIANG Xin
YANG Sili
LYU Guocang
WEI Jingxuan
LI Qiao
Abstract：Wideband signal detection framework enables to realize detection,identification,and time-fre-quency localization of multiple signals in the wideband RF systems with object detection being combined with spectrograms based on deep learning,whereas directly applied original network architecture is diffi-cult to achieve optimal signal detection performance on actual task datasets.For the above-mentioned rea-sons,this paper proposes a network architecture,SignalNet,for voice signal detection task,which is de-coupled for task-oriented optimization according to the characteristics of the voice signals and task dataset.Specifically,the backbone network is streamlined,which is responsible for feature extraction,a neck net-work that comprises the multi-scale time-frequency feature context fusion and gating attention modules is introduced,and the traditional anchor-based detection head is replaced with an anchor-free one.The expe-rimental results show that the proposed network architecture achieves the optimal detection performance for the voice signal detection task,mAP reaches not only 97.42％,but also is in maintaining fewer model parameters and faster inference speed.
Keywords：signal detection and recognitiondeep learningnetwork architecture designtask-orientedfea-ture fusion
Publication Date：2025-06-25
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：9( 26-34 )