On Feature Learning for Titi Monkey Activity Detection

Aditya Ravuri; Jen Muir; Neil D. Lawrence

Back to publications

On Feature Learning for Titi Monkey Activity Detection

Aditya Ravuri, Jen Muir, Neil D. Lawrence

, 2024.

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.

Links

Cite this Paper

BibTeX


@Misc{publications/on-feature-learning-for-titi-monkey-activity-detection,
  title = 	 {On Feature Learning for Titi Monkey Activity Detection},
  author = 	 {Ravuri, Aditya and Muir, Jen and Lawrence, Neil D.},
  year = 	 {2024},
  url = 	 {/publications/on-feature-learning-for-titi-monkey-activity-detection.html},
  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.
}
}

Endnote

%0 Generic
%T On Feature Learning for Titi Monkey Activity Detection
%A Aditya Ravuri
%A Jen Muir
%A Neil D. Lawrence
%D 2024	
%F publications/on-feature-learning-for-titi-monkey-activity-detection
%U /publications/on-feature-learning-for-titi-monkey-activity-detection.html
%X 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.

RIS


TY  - GEN
TI  - On Feature Learning for Titi Monkey Activity Detection
AU  - Aditya Ravuri
AU  - Jen Muir
AU  - Neil D. Lawrence
DA  - 2024/07/01	
ID  - publications/on-feature-learning-for-titi-monkey-activity-detection
UR  - /publications/on-feature-learning-for-titi-monkey-activity-detection.html
AB  - 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.

ER  -

APA


Ravuri, A., Muir, J. & Lawrence, N.D.. (2024). On Feature Learning for Titi Monkey Activity Detection.  Available from /publications/on-feature-learning-for-titi-monkey-activity-detection.html.