Introducing a Central African Primate Vocalisation Dataset for Automated Species Classification

TL;DR

This paper presents a new primate vocalisation dataset from Cameroon and demonstrates a classifier achieving up to 82% UAR for four-species classification, aiding wildlife monitoring.

Contribution

It introduces a novel dataset of primate vocalisations recorded in semi-natural conditions and provides initial classifier results for species detection.

Findings

Achieved up to 82% UAR in four-species classification

Developed an automatic vocalisation detection method

Provided a valuable dataset for wildlife monitoring

Abstract

Automated classification of animal vocalisations is a potentially powerful wildlife monitoring tool. Training robust classifiers requires sizable annotated datasets, which are not easily recorded in the wild. To circumvent this problem, we recorded four primate species under semi-natural conditions in a wildlife sanctuary in Cameroon with the objective to train a classifier capable of detecting species in the wild. Here, we introduce the collected dataset, describe our approach and initial results of classifier development. To increase the efficiency of the annotation process, we condensed the recordings with an energy/change based automatic vocalisation detection. Segmenting the annotated chunks into training, validation and test sets, initial results reveal up to 82% unweighted average recall (UAR) test set performance in four-class primate species classification.