Automated detection of Bornean white-bearded gibbon (Hylobates albibarbis) vocalisations using an open-source framework for deep learning
Passive acoustic monitoring is a promising tool for monitoring at-risk populations of vocal species, yet extracting relevant information from large acoustic datasets can be time-consuming, creating a bottleneck at the point of analysis. To address this, we adapted an open-source framework for deep learning in bioacoustics to automatically detect Bornean white-bearded gibbon (Hylobates albibarbis) "great call" vocalisations in a long-term acoustic dataset from a rainforest location in Borneo. We describe the steps involved in developing this solution, including collecting audio recordings, developing training and testing datasets, training neural network models, and evaluating model performance. Our best model performed at a satisfactory level (F score = 0.87), identifying 98% of the highest-quality calls from 90 hours of manually-annotated audio recordings and greatly reduced analysis times when compared to a human observer. We found no significant difference in the temporal distribution of great call detections between the manual annotations and the models output. Future work should seek to apply our model to long-term acoustic datasets to understand spatiotemporal variations in H. albibarbis calling activity. Overall, we present a roadmap for applying deep learning to identify the vocalisations of species of interest which can be adapted for monitoring other endangered vocalising species.