A Deep and Recurrent Architecture for Primate Vocalization Classification

Wildlife monitoring is an essential part of most conservation efforts where one of the many building blocks is acoustic monitoring. Acoustic monitoring has the advantage of being non-invasive and applicable in areas of high vegetation. In this work, we present a deep and recurrent architecture for the classification of primate vocalizations that is based upon well proven modules such as bidirectional Long Short-Term Memory neural networks, pooling, normalized softmax and focal loss. Additionally, we apply Bayesian optimization to obtain a suitable set of hyperparameters. We test our approach on a recently published dataset of primate vocalizations that were recorded in an African wildlife sanctuary. Using an ensemble of the best five models found during hyperparameter optimization on the development set, we achieve a Unweighted Average Recall of 89.3% on the test set. Our approach outperforms the best baseline, an ensemble of various deep and shallow classifiers, which achieves a UAR of 87.5%.

Automated summary

This research introduces a deep and recurrent neural network architecture for acoustic monitoring of primate vocalizations, achieving a high recall rate on a dataset from an African wildlife sanctuary. The study employs Bayesian optimization to obtain suitable hyperparameters and outperforms baseline models with an ensemble of deep and shallow classifiers.