File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls

TitleImproving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls
Authors
Issue Date13-Apr-2023
PublisherPublic Library of Science
Citation
PLoS Computational Biology, 2023, v. 19, n. 4, p. e1010325 How to Cite?
Abstract

Despite the accumulation of data and studies, deciphering animal vocal communication remains challenging. In most cases, researchers must deal with the sparse recordings composing Small, Unbalanced, Noisy, but Genuine (SUNG) datasets. SUNG datasets are characterized by a limited number of recordings, most often noisy, and unbalanced in number between the individuals or categories of vocalizations. SUNG datasets therefore offer a valuable but inevitably distorted vision of communication systems. Adopting the best practices in their analysis is essential to effectively extract the available information and draw reliable conclusions. Here we show that the most recent advances in machine learning applied to a SUNG dataset succeed in unraveling the complex vocal repertoire of the bonobo, and we propose a workflow that can be effective with other animal species. We implement acoustic parameterization in three feature spaces and run a Supervised Uniform Manifold Approximation and Projection (S-UMAP) to evaluate how call types and individual signatures cluster in the bonobo acoustic space. We then implement three classification algorithms (Support Vector Machine, xgboost, neural networks) and their combination to explore the structure and variability of bonobo calls, as well as the robustness of the individual signature they encode. We underscore how classification performance is affected by the feature set and identify the most informative features. In addition, we highlight the need to address data leakage in the evaluation of classification performance to avoid misleading interpretations. Our results lead to identifying several practical approaches that are generalizable to any other animal communication system. To improve the reliability and replicability of vocal communication studies with SUNG datasets, we thus recommend: i) comparing several acoustic parameterizations; ii) visualizing the dataset with supervised UMAP to examine the species acoustic space; iii) adopting Support Vector Machines as the baseline classification approach; iv) explicitly evaluating data leakage and possibly implementing a mitigation strategy.


Persistent Identifierhttp://hdl.handle.net/10722/331143
ISSN
2023 Impact Factor: 3.8
2023 SCImago Journal Rankings: 1.652
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorArnaud, V-
dc.contributor.authorPellegrino, F-
dc.contributor.authorKeenan, S-
dc.contributor.authorSt-Gelais, X-
dc.contributor.authorMathevon, N-
dc.contributor.authorLevrero, F-
dc.contributor.authorCoupe, C-
dc.date.accessioned2023-09-21T06:53:06Z-
dc.date.available2023-09-21T06:53:06Z-
dc.date.issued2023-04-13-
dc.identifier.citationPLoS Computational Biology, 2023, v. 19, n. 4, p. e1010325-
dc.identifier.issn1553-734X-
dc.identifier.urihttp://hdl.handle.net/10722/331143-
dc.description.abstract<p>Despite the accumulation of data and studies, deciphering animal vocal communication remains challenging. In most cases, researchers must deal with the sparse recordings composing Small, Unbalanced, Noisy, but Genuine (SUNG) datasets. SUNG datasets are characterized by a limited number of recordings, most often noisy, and unbalanced in number between the individuals or categories of vocalizations. SUNG datasets therefore offer a valuable but inevitably distorted vision of communication systems. Adopting the best practices in their analysis is essential to effectively extract the available information and draw reliable conclusions. Here we show that the most recent advances in machine learning applied to a SUNG dataset succeed in unraveling the complex vocal repertoire of the bonobo, and we propose a workflow that can be effective with other animal species. We implement acoustic parameterization in three feature spaces and run a Supervised Uniform Manifold Approximation and Projection (S-UMAP) to evaluate how call types and individual signatures cluster in the bonobo acoustic space. We then implement three classification algorithms (Support Vector Machine, xgboost, neural networks) and their combination to explore the structure and variability of bonobo calls, as well as the robustness of the individual signature they encode. We underscore how classification performance is affected by the feature set and identify the most informative features. In addition, we highlight the need to address data leakage in the evaluation of classification performance to avoid misleading interpretations. Our results lead to identifying several practical approaches that are generalizable to any other animal communication system. To improve the reliability and replicability of vocal communication studies with SUNG datasets, we thus recommend: i) comparing several acoustic parameterizations; ii) visualizing the dataset with supervised UMAP to examine the species acoustic space; iii) adopting Support Vector Machines as the baseline classification approach; iv) explicitly evaluating data leakage and possibly implementing a mitigation strategy.<br></p>-
dc.languageeng-
dc.publisherPublic Library of Science-
dc.relation.ispartofPLoS Computational Biology-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleImproving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls-
dc.typeArticle-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1371/journal.pcbi.1010325-
dc.identifier.scopuseid_2-s2.0-85153898096-
dc.identifier.volume19-
dc.identifier.issue4-
dc.identifier.spagee1010325-
dc.identifier.eissn1553-7358-
dc.identifier.isiWOS:000971878900001-
dc.identifier.issnl1553-734X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats