Acoustic evaluation of a neural network dedicated to the detection of animal vocalisations

TL;DR

This paper introduces an acoustic analysis method for neural network-based animal vocalization detection, enabling performance evaluation, system optimization, and estimation of detection range and call density in ecological monitoring.

Contribution

It presents a novel acoustic analysis approach that relates signal-to-noise ratio to detection probability, improving evaluation and optimization of neural detection systems.

Findings

The method relates synthetic signal SNR to detection probability.

It enables optimization of neural network training.

It allows modeling of detection distance and call density.

Abstract

The accessibility of long-duration recorders, adapted to sometimes demanding field conditions, has enabled the deployment of extensive animal population monitoring campaigns through ecoacoustics. The effectiveness of automatic signal detection methods, increasingly based on neural approaches, is frequently evaluated solely through machine learning metrics, while acoustic analysis of performance remains rare. As part of the acoustic monitoring of Rock Ptarmigan populations, we propose here a simple method for acoustic analysis of the detection system's performance. The proposed measure is based on relating the signal-to-noise ratio of synthetic signals to their probability of detection. We show how this measure provides information about the system and allows optimisation of its training. We also show how it enables modelling of the detection distance, thus offering the possibility of evaluating its dynamics according to the sound environment and accessing an estimation of the spatial density of calls.