@misc{10481/93662,
year = {2024},
month = {7},
url = {https://hdl.handle.net/10481/93662},
abstract = {The scarcity of labelled data makes training Deep
Neural Network (DNN) models in bioacoustic applications challenging.
In typical bioacoustics applications, manually labelling
the required amount of data can be prohibitively expensive. To
effectively identify both new and current classes, DNN models
must continue to learn new features from a modest amount
of fresh data. Active Learning (AL) is an approach that can
help with this learning while requiring little labelling effort.
Nevertheless, the use of fixed feature extraction approaches limits
feature quality, resulting in underutilization of the benefits of
AL. We describe an AL framework that addresses this issue by
incorporating feature extraction into the AL loop and refining
the feature extractor after each round of manual annotation. In
addition, we use raw audio processing rather than spectrograms,
which is a novel approach. Experiments reveal that the proposed
AL framework requires 14.3%, 66.7%, and 47.4% less labelling
effort on benchmark audio datasets ESC-50, UrbanSound8k, and
InsectWingBeat, respectively, for a large DNN model and similar
savings on a microcontroller-based counterpart. Furthermore, we
showcase the practical relevance of our study by incorporating
data from conservation biology projects. All codes are publicly
available on GitHub.},
organization = {Australian Research
Council under grant DE19010 0 045},
publisher = {IEEE},
keywords = {Deep Learning},
keywords = {Active Learning},
keywords = {Deep Active Learning},
title = {Deep Active Audio Feature Learning in Resource-Constrained Environments},
doi = {10.48550/arXiv.2308.13201},
author = {Mohaimenuzzaman, Md and Bergmeir, Christoph Norbert and Meyer, Bernd},
}