High-Fidelity Sonar Waveform Synthesis With Multi-Band Adversarial Networks
- 23 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1160-1164
Abstract
Recent advances in underwater sonar detection have highlighted the challenges of acquiring real-world sonar data due to experimental costs and environmental constraints. While deep learning-based methods have shown promise in sonar synthesis, existing approaches often lack fidelity in waveform generation. This manuscript proposes Multi-Band HiFi-GAN, a high-fidelity synthesis method that incorporates a multi-band processing module based on a Pseudo-QMF bank for spectrally-efficient sub-band decomposition, and Multi-Band STFT Discriminator (MBSD) that jointly models time-frequency structures and mitigates aliasing artifacts. Additionally, we design a multi-resolution STFT loss to enhance convergence. Evaluated on DeepShip dataset using Fréchet Audio Distance (FAD), our method demonstrates superior performance, achieving a lower FAD score than existing approaches. Augmenting real training data with synthesized samples improves target classification accuracy to 96.94% at a 100% mixing ratio. The work provides a practical data augmentation solution for underwater acoustic systems, improving synthesis fidelity.Keywords
Funding Information
- Zhejiang Provincial Natural Science Foundation of China (LQN26F030024)
- Central Government-guided local Science and Technology development (2025ZY01045)
- Stable Supporting Fund of Acoustic Science and Technology Laboratory (JCKYS2024604SSJS00502)
- National Natural Science Foundation of China (U20B2074)
- National Natural Science Foundation of China (62471169)
- Zhejiang Provincial Key Laboratory of Brain Computer Collaborative Intelligence Technology and Applications (2025E10015)
This publication has 19 references indexed in Scilit:
- Underwater Acoustic Signal Recognition with Small Transfer Learning-based Training Samples2024
- DeepShip: An underwater acoustic benchmark dataset and a separable convolution based autoencoder for classificationExpert Systems with Applications, 2021
- Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentationApplied Acoustics, 2021
- Parallel Wavegan: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-Resolution Spectrogram2020
- Waveglow: A Flow-based Generative Network for Speech Synthesis2019
- Least Squares Generative Adversarial Networks2017
- Audio Set: An ontology and human-labeled dataset for audio events2017
- CNN architectures for large-scale audio classification2017
- Multi-everything Sonar Simulator (MESS)2006
- Near-perfect-reconstruction pseudo-QMF banksIEEE Transactions on Signal Processing, 1994