Pseudo Ship-radiated Noise Generation Based on Adversarial Learning

Abstract

The demand for acoustic positioning is increasing in various fields, meanwhile, it is very important to disturb acoustic positioning for underwater acoustics countermeasure and ship stealth technology. In this paper, a one-dimensional (ID) deep neural network based on adversarial learning to generate pseudo ship-radiated noises is presented, and a ID convolutional network for classification is also given for evaluating the generated pseudo ship-radiated noises. The experimental results show that the proposed solution is effective to generate pseudo ship-radiated noises.