# Automatic Detection and Compression for Passive Acoustic Monitoring of the African Forest Elephant

## TL;DR

This paper presents a machine learning approach for detecting and compressing African Forest Elephant calls in passive acoustic monitoring, enabling efficient, real-time wildlife surveillance in remote habitats.

## Contribution

It introduces a large labeled dataset and a novel end-to-end differentiable compression method tailored for low-frequency animal calls, advancing passive acoustic monitoring techniques.

## Key findings

- Improved classification and segmentation accuracy for elephant calls.
- Significant reduction in data size with the new compression method.
- Enhanced real-time detection capabilities in bandwidth-constrained environments.

## Abstract

In this work, we consider applying machine learning to the analysis and compression of audio signals in the context of monitoring elephants in sub-Saharan Africa. Earth's biodiversity is increasingly under threat by sources of anthropogenic change (e.g. resource extraction, land use change, and climate change) and surveying animal populations is critical for developing conservation strategies. However, manually monitoring tropical forests or deep oceans is intractable. For species that communicate acoustically, researchers have argued for placing audio recorders in the habitats as a cost-effective and non-invasive method, a strategy known as passive acoustic monitoring (PAM). In collaboration with conservation efforts, we construct a large labeled dataset of passive acoustic recordings of the African Forest Elephant via crowdsourcing, compromising thousands of hours of recordings in the wild. Using state-of-the-art techniques in artificial intelligence we improve upon previously proposed methods for passive acoustic monitoring for classification and segmentation. In real-time detection of elephant calls, network bandwidth quickly becomes a bottleneck and efficient ways to compress the data are needed. Most audio compression schemes are aimed at human listeners and are unsuitable for low-frequency elephant calls. To remedy this, we provide a novel end-to-end differentiable method for compression of audio signals that can be adapted to acoustic monitoring of any species and dramatically improves over naive coding strategies.