Propeller Noise Detection with Deep Learning

Abstract

Due to the complexity of environment and source modelling, underwater target detection is a rather challenging task. In the Deep Learning community, many attempts were made to deal with this problem, mainly through expert features, but few assessed the benefit of using raw acoustic signals. In this paper, we propose a new model of underwater propeller noise as well as its optimal statistical detector for detecting the presence of propeller in acoustic signal. We then design a deep learning architecture which approximates this optimal detector using only some training signal samples. Numerical simulations confirm the efficiency of the approach.