Back to publications
On Feature Learning for Titi Monkey Activity Detection
Paper Details
Published: 2024/07/01
DOI: 10.48550/arXiv.2407.01452
ARXIV ID: 2407.01452v1
This paper introduces a robust machine learning framework for the detection of vocal activities of Coppery titi monkeys. Utilizing a combination of MFCC features and a bidirectional LSTM-based classifier, the authors effectively address the challenges posed by the small amount of expert-annotated vocal data available. This approach significantly reduces false positives and improves the accuracy of call detection in bioacoustic research. Initial results demonstrate an accuracy of 95% on instance predictions, highlighting the effectiveness of our model in identifying and classifying complex vocal patterns in environmental audio recordings. Moreover, the authors show how call classification can be done downstream, paving the way for real-world monitoring.
