Значок книги

Generative AI-based data augmentation for improved bioacoustic classification in noisy environments

Сохранить в:
Опубликовано в::arXiv.org (Dec 2, 2024), p. n/a
Главный автор: Gibbons, Anthony
Другие авторы: King, Emma, Donohue, Ian, Parnell, Andrew
Опубликовано:
Cornell University Library, arXiv.org
Предметы:
Background noise
Probabilistic models
Data augmentation
Accuracy
Wind power
Land use
Wind farms
Spectrograms
Generative artificial intelligence
Classification
Generative adversarial networks
Wind turbines
Audio data
Species classification
Machine learning
Synthetic data
Online-ссылка:Citation/Abstract
Full text outside of ProQuest
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!
Краткий обзор:1. Obtaining data to train robust artificial intelligence (AI)-based models for species classification can be challenging, particularly for rare species. Data augmentation can boost classification accuracy by increasing the diversity of training data and is cheaper to obtain than expert-labelled data. However, many classic image-based augmentation techniques are not suitable for audio spectrograms. 2. We investigate two generative AI models as data augmentation tools to synthesise spectrograms and supplement audio data: Auxiliary Classifier Generative Adversarial Networks (ACGAN) and Denoising Diffusion Probabilistic Models (DDPMs). The latter performed particularly well in terms of both realism of generated spectrograms and accuracy in a resulting classification task. 3. Alongside these new approaches, we present a new audio data set of 640 hours of bird calls from wind farm sites in Ireland, approximately 800 samples of which have been labelled by experts. Wind farm data are particularly challenging for classification models given the background wind and turbine noise. 4. Training an ensemble of classification models on real and synthetic data combined gave 92.6% accuracy (and 90.5% with just the real data) when compared with highly confident BirdNET predictions. 5. Our approach can be used to augment acoustic signals for more species and other land-use types, and has the potential to bring about a step-change in our capacity to develop reliable AI-based detection of rare species. Our code is available at https://github.com/gibbona1/ SpectrogramGenAI.
ISSN:2331-8422
Источник:Engineering Database