On Feature Learning for Titi Monkey Activity Detection

TL;DR

This paper presents a machine learning framework using MFCC features and bidirectional LSTM to accurately detect and classify titi monkey vocalizations, overcoming limited annotated data and enhancing bioacoustic monitoring.

Contribution

It introduces a novel LSTM-based approach tailored for small datasets to improve vocal activity detection in bioacoustic research.

Findings

Achieved 95% accuracy in call detection

Reduced false positives significantly

Demonstrated effective call classification in environmental recordings

Abstract

This paper, a technical summary of our preceding publication, 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, we effectively address the challenges posed by the small amount of expert-annotated vocal data available. Our 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, we show how call classification can be done downstream, paving the way for real-world monitoring.