Deep Learning on Small Datasets to Classify Mammalian Vocalizations

Rodrigo Manriquez, Sonja A. Kotz, Andrea Ravignani, Bart De Boer

Onderzoeksoutput: Conference paper

6 Downloads (Pure)

Samenvatting

Deep learning algorithms are increasingly used in many fields outside of artificial intelligence, including bioacoustics. Among many possible applications of deep learning to bioacoustics, typical ones include call identification, species recognition, and acoustic features classification. However, the implementation of deep learning algorithms is limited as bioacoustic databases are often rather small and thus lack sufficient data to properly train neural networks. Improper training leads to problems like overfitting and lack of generalization which, in turn, affect performance. Here, we address the most common challenges that bioacousticians face when training a deep neural network in a classification task. We present and explain useful techniques such as pre-training and data augmentation, and emphasize applying them in an efficient and meaningful way to not alter distinctive features or specific stimulus features such as fundamental frequency. We present an example application of these techniques in a classification task, where we perform species identification in a database of phylogenetically distant mammals, each with a limited number of calls. We aimed at developing a general framework on how to apply deep learning algorithms to small- and larger-scale bioacoustic datasets.
Originele taal-2English
TitelProceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023
UitgeverijCentro Congressi Internazionale Srl
Pagina's4687-4690
Aantal pagina's4
ISBN van geprinte versie978-88-88942-67-4
DOI's
StatusPublished - 2023
EvenementProceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023 : Forum Acusticum 2023 - Torino, Italy
Duur: 11 sep 202315 sep 2023

Conference

ConferenceProceedings of the 10th Convention of the European Acoustics Association Forum Acusticum 2023 : Forum Acusticum 2023
Land/RegioItaly
StadTorino
Periode11/09/2315/09/23

Vingerafdruk

Duik in de onderzoeksthema's van 'Deep Learning on Small Datasets to Classify Mammalian Vocalizations'. Samen vormen ze een unieke vingerafdruk.

Citeer dit