A Lightweight Channel-Frequency Joint Attention Network for Underwater Ship-Radiated Noise Separation.
- 1School of Computer Science, Xi'an Polytechnic University, Xi'an 710600, China.
Abstract
Underwater acoustic signals (UAS) in marine environments are often contaminated by noise from biological activity, ocean waves, and equipment. Under low signal-to-noise ratio (SNR) conditions, target ship-radiated components and background noise are strongly mixed, making reliable underwater detection, recognition, and communication challenging. To address this problem, this paper proposes Multi-Scale TCN, DPRNN, and Attention TasNet (MSDA-TasNet), a lightweight end-to-end source separation network for underwater ship-radiated noise. The proposed method combines time-domain convolutional encoding, a dual-path recurrent neural network (DPRNN), and a multi-scale temporal convolutional network (multi-scale TCN) to model both short-term details and long-term dependencies of UAS. To further enhance target-aware feature representation, this paper designs a novel channel-frequency attention mechanism that adaptively emphasizes target-related spectral cues. Experiments on two underwater acoustic datasets show that MSDA-TasNet achieves better separation performance than several representative baselines in terms of Signal-to-Distortion Ratio (SDR), Scale-Invariant Signal-to-Distortion Ratio (SI-SDR), SDR improvement (SDRi), SI-SDR improvement (SI-SDRi), and Segmental Signal-to-Distortion Ratio (SegSDR). The results indicate that the proposed network can improve target signal recovery under complex underwater acoustic noise while maintaining a relatively low parameter count and computational cost.
Related
- XCAT-UIR: explainable cross-attention guided ConvNeXt-transformer framework for underwater image restoration systems
- A lightweight underwater biological object detector with enhanced cross-scale feature interaction
- PAUNet: A Lightweight Network for Real-Time Underwater Image Enhancement.
- Energy-dependent underwater abrasion behavior of sustainable lightweight concrete incorporating agro-waste aggregates and natural fibers under rotational hydraulic conditions
- YOLO-CBNet: A robust attention-enhanced detection framework for underwater fish recognition in aquaculture environments
BibTeX
@article{dong2026lightweight,
title = {{A Lightweight Channel-Frequency Joint Attention Network for Underwater Ship-Radiated Noise Separation.}},
author = {Junxian Dong and Qiong Yang and Ying Li},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/s26206382},
url = {https://europepmc.org/article/MED/42944242},
note = {CC BY},
}
RIS
TY - JOUR
TI - A Lightweight Channel-Frequency Joint Attention Network for Underwater Ship-Radiated Noise Separation.
AU - Junxian Dong
AU - Qiong Yang
AU - Ying Li
PY - 2026
DA - 2026/10/09
JO - Sensors (Basel, Switzerland)
DO - 10.3390/s26206382
UR - https://europepmc.org/article/MED/42944242
AB - Underwater acoustic signals (UAS) in marine environments are often contaminated by noise from biological activity, ocean waves, and equipment. Under low signal-to-noise ratio (SNR) conditions, target ship-radiated components and background noise are strongly mixed, making reliable underwater detection, recognition, and communication challenging. To address this problem, this paper proposes Multi-Scale TCN, DPRNN, and Attention TasNet (MSDA-TasNet), a lightweight end-to-end source separation network for underwater ship-radiated noise. The proposed method combines time-domain convolutional encoding, a dual-path recurrent neural network (DPRNN), and a multi-scale temporal convolutional network (multi-scale TCN) to model both short-term details and long-term dependencies of UAS. To further enhance target-aware feature representation, this paper designs a novel channel-frequency attention mechanism that adaptively emphasizes target-related spectral cues. Experiments on two underwater acoustic datasets show that MSDA-TasNet achieves better separation performance than several representative baselines in terms of Signal-to-Distortion Ratio (SDR), Scale-Invariant Signal-to-Distortion Ratio (SI-SDR), SDR improvement (SDRi), SI-SDR improvement (SI-SDRi), and Segmental Signal-to-Distortion Ratio (SegSDR). The results indicate that the proposed network can improve target signal recovery under complex underwater acoustic noise while maintaining a relatively low parameter count and computational cost.
SN - 1424-8220
ER -