Bi-class classification of humpback whale sound units against complex background noise with Deep Convolution Neural Network

TL;DR

This paper investigates using deep convolutional neural networks to detect humpback whale sounds amidst complex background noise, demonstrating improved performance over traditional spectrogram methods.

Contribution

It introduces a CNN-based approach for whale sound detection and compares its effectiveness against classical FFT-based spectrogram methods.

Findings

CNN features outperform traditional spectrogram representations

Higher accuracy achieved in whale sound classification

Effective detection across various background noise types

Abstract

Automatically detecting sound units of humpback whales in complex time-varying background noises is a current challenge for scientists. In this paper, we explore the applicability of Convolution Neural Network (CNN) method for this task. In the evaluation stage, we present 6 bi-class classification experimentations of whale sound detection against different background noise types (e.g., rain, wind). In comparison to classical FFT-based representation like spectrograms, we showed that the use of image-based pretrained CNN features brought higher performance to classify whale sounds and background noise.