Comparing methodologies for classification of zebra finch distance calls

Sahu, Prateek K.; Campbell, Kimberley A.; Oprea, Alexandra; Phillmore, Leslie S.; Sturdy, Christopher B.

doi:10.1121/10.0011401

Cited by 1 publication

(1 citation statement)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has become the standard approach for bioacoustic analysis and it is still routinely used nowadays despite its limitations (e.g. [ 18 , 19 ] in chimpanzees; [ 20 ] in Dwarf mongoose; [ 21 ] in woodpeckers, among recent publications; see also [ 22 ] in zebra finch for a comparison with two other classifiers). Being derived from classical DFA, it indeed shares its main shortcomings: it is quite sensitive to the presence of outliers in the dataset and the maximal number of features as well as the number of observations that can be considered are quite constrained by the dataset structure and the dependency among the observations (see [ 17 ] for a thorough discussion).…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

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.

show abstract