Automated Detection of Dolphin Whistles with Convolutional Networks and Transfer Learning

TL;DR

This paper demonstrates that convolutional neural networks, combined with transfer learning, can effectively detect dolphin whistles in underwater recordings, outperforming traditional methods and aiding marine ecosystem monitoring.

Contribution

The study introduces a CNN-based approach with transfer learning for dolphin whistle detection, showing significant improvements over existing techniques.

Findings

CNN outperforms traditional detection methods.

System detects signals amidst ambient noise.

Reduces false positives and negatives.

Abstract

Effective conservation of maritime environments and wildlife management of endangered species require the implementation of efficient, accurate and scalable solutions for environmental monitoring. Ecoacoustics offers the advantages of non-invasive, long-duration sampling of environmental sounds and has the potential to become the reference tool for biodiversity surveying. However, the analysis and interpretation of acoustic data is a time-consuming process that often requires a great amount of human supervision. This issue might be tackled by exploiting modern techniques for automatic audio signal analysis, which have recently achieved impressive performance thanks to the advances in deep learning research. In this paper we show that convolutional neural networks can indeed significantly outperform traditional automatic methods in a challenging detection task: identification of dolphin whistles from underwater audio recordings. The proposed system can detect signals even in the presence of ambient noise, at the same time consistently reducing the likelihood of producing false positives and false negatives. Our results further support the adoption of artificial intelligence technology to improve the automatic monitoring of marine ecosystems.