Ambient-noise Free Generation of Clean Underwater Ship Engine Audios from Hydrophones using Generative Adversarial Networks. (May 2022)

• Record Type: Journal Article
• Authors: Ashraf, Hina; Shah, Babar; Soomro, Afaque Manzoor; Safdar, Qurat-ul-Ain; Halim, Zahid; Shah, Said Khalid
• Is Part Of: Computers & electrical engineering. Volume 100(2022)
• Publication Date: 2022-05
• Subjects: Hydrophones -- ambient-noise -- generative adversarial networks (GAN) -- denoising -- signal-to-noise ratio (SNR); Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.107970
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: An audio denoising GAN framework for underwater acoustic signal denoising The AN-GAN generates clean data and distinguishes the real measurement from a fake. Proposed AN-GAN incorporates a fully convolutional generator for generating clean data Integrates a patch discriminator in time domain. The proposed network removes ambient noise and improved SNR. Abstract: Generative adversarial networks (GANs) have been extensively used in image domain showing promising results in generating and learning data distributions in the absence of clean data. However, the audio domain, specially underwater acoustics are not yet fully explored in reporting the efficiency and applicability of GANs. We propose an audio GAN framework called ambient noise-free GAN (AN-GAN) to address the underwater acoustic signal denoising problem by removing the background ambient noise. The proposed AN-GAN can learn a clean audio generation with improved signal-to-noise ratio (SNR) given only the noisy samples from the underwater audio dataset. The simulated and real-time data collected from online available source ShipsEar, is used for the analysis and validation purpose. The comparative analysis shows an average percentage improvement of proposed AN-GAN with GAN-based and conventional statistical underwater denoising methods as 6.27% for UWAR-GAN, 227% for Wavelet denoising, 247% for EMD and 65% for Wiener technique. Graphical abstract: Image, graphical abstract