Underwater Acoustic Signal Denoising Algorithms: A Survey of the State-of-the-art

TL;DR

This survey addresses the problem of denoising underwater acoustic signals (UAS) in challenging marine environments. It comprehensively categorizes approaches into conventional, decomposition-based, and deep-learning, detailing foundational methods such as DWT, EMD, VMD, EWT, and modern DL architectures with various input forms and loss functions. The paper highlights open questions, including optimal decomposition levels, dataset limitations, and the need for online, automated learning and ensemble strategies. By mapping datasets, metrics, and applications, it provides a practical roadmap for researchers and engineers to improve UAS denoising performance in real-time underwater scenarios.

Abstract

This paper comprehensively reviews recent advances in underwater acoustic signal denoising, an area critical for improving the reliability and clarity of underwater communication and monitoring systems. Despite significant progress in the field, the complex nature of underwater environments poses unique challenges that complicate the denoising process. We begin by outlining the fundamental challenges associated with underwater acoustic signal processing, including signal attenuation, noise variability, and the impact of environmental factors. The review then systematically categorizes and discusses various denoising algorithms, such as conventional, decomposition-based, and learning-based techniques, highlighting their applications, advantages, and limitations. Evaluation metrics and experimental datasets are also reviewed. The paper concludes with a list of open questions and recommendations for future research directions, emphasizing the need for developing more robust denoising techniques that can adapt to the dynamic underwater acoustic environment.

Figures (5)

• Figure 1: Framework of underwater acoustic signal denoising.
• Figure 2: Bibliometric analysis of UAS denoising from 2011 to 2024.
• Figure 3: Underwater scenario illustrating complex noise sources.
• Figure 4: Framework of decomposition-based UAS denoising.
• Figure 5: Framework of DL-based Autoencoder UAS denoising algorithms.