Publication Date:
2022-09-14
Description:
© The Author(s), 2022. This article is distributed under the terms of the Creative Commons Attribution License. The definitive version was published in Thomas, M., Jensen, F. H., Averly, B., Demartsev, V., Manser, M. B., Sainburg, T., Roch, M. A., & Strandburg-Peshkin, A. A practical guide for generating unsupervised, spectrogram-based latent space representations of animal vocalizations. The Journal of Animal Ecology, 91(8), (2022): 1567– 1581, https://doi.org/10.1111/1365-2656.13754.
Description:
1. Background: The manual detection, analysis and classification of animal vocalizations in acoustic recordings is laborious and requires expert knowledge. Hence, there is a need for objective, generalizable methods that detect underlying patterns in these data, categorize sounds into distinct groups and quantify similarities between them. Among all computational methods that have been proposed to accomplish this, neighbourhood-based dimensionality reduction of spectrograms to produce a latent space representation of calls stands out for its conceptual simplicity and effectiveness.
2. Goal of the study/what was done: Using a dataset of manually annotated meerkat Suricata suricatta vocalizations, we demonstrate how this method can be used to obtain meaningful latent space representations that reflect the established taxonomy of call types. We analyse strengths and weaknesses of the proposed approach, give recommendations for its usage and show application examples, such as the classification of ambiguous calls and the detection of mislabelled calls.
3. What this means: All analyses are accompanied by example code to help researchers realize the potential of this method for the study of animal vocalizations.
Description:
This work was supported by HFSP Research Grant RGP0051/2019 to ASP, MBM and MAR, and funded by the Deutsche Forschungsgemeinschaft (DFG) under Germany's Excellence Strategy (EXC-2117-422037984). ASP received additional funding from the Gips-Schüle Stiftung, the Zukunftskolleg at the University of Konstanz and the Max-Planck-Institute of Animal Behaviour. VD was funded by the Minerva Stiftung and Alexander von Humboldt Foundation.
Keywords:
animal sounds
;
animal vocalizations
;
bioacoustics
;
call classification
;
dimensionality reduction
;
spectrogram
;
UMAP
;
unsupervised learning
Repository Name:
Woods Hole Open Access Server
Type:
Article
Permalink
