Introducing a Central African Primate Vocalisation Dataset for Automated Species Classification
This work addresses the challenge of wildlife monitoring for conservationists by providing a dataset and method for species classification, but it is incremental as it applies existing techniques to new data.
The authors tackled the problem of automated primate species classification by introducing a new dataset of Central African primate vocalizations recorded in a wildlife sanctuary, achieving up to 82% unweighted average recall in a four-class classification task.
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.