Improving the workflow to crack Small, Unbalanced, Noisy, but Genuine (SUNG) datasets in bioacoustics: The case of bonobo calls
Open Access
- 13 April 2023
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 19 (4) , e1010325
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.Keywords
All Related Versions
Funding Information
- Ministère de l’Enseignement Supérieur et de la Recherche
- Ecole Doctorale SIS of the University of Saint-Etienne (n° ENS 2012/398)
- Université du Québec à Chicoutimi
- Université Jean Monnet Saint-Etienne
- LabEx ASLAN (ANR-10-LABX-0081)
- Agence Nationale de la Recherche (Investments for the Future program (ANR-11-IDEX-0007))
- Institut Universitaire de France
- Social Sciences and Humanities Research Council of Canada
This publication has 114 references indexed in Scilit:
- Vocal Signature in Wild Infant ChimpanzeesAmerican Journal of Primatology, 2012
- Segmental concatenation of individual signatures and context cues in banded mongoose (Mungos mungo) close callsBMC Biology, 2012
- Bonobos Extract Meaning from Call SequencesPLOS ONE, 2011
- Acoustic correlates of individuality in the vocal repertoire of a nocturnal primate (Microcebus murinus)The Journal of the Acoustical Society of America, 2011
- What the hyena's laugh tells: Sex, age, dominance and individual signature in the giggling call of Crocuta crocutaBMC Ecology, 2010
- Acoustic features contributing to the individuality of wild agile gibbon (Hylobates agilis agilis) songsAmerican Journal of Primatology, 2007
- Signature whistle shape conveys identity information to bottlenose dolphinsProceedings of the National Academy of Sciences, 2006
- SUBHARMONICS, BIPHONATION, AND DETERMINISTIC CHAOS IN MAMMAL VOCALIZATIONBioacoustics, 1998
- Spectral-shape features versus formants as acoustic correlates for vowelsThe Journal of the Acoustical Society of America, 1993
- Ridge Regression: Biased Estimation for Nonorthogonal ProblemsTechnometrics, 1970