Identification of dialects and individuals of globally threatened yellow cardinals using neural networks

BOCACCIO, HERNAN; DOMINGUEZ, MARISOL; MAHLER, BETTINA; REBOREDA, JUAN CARLOS; BERNARDO GABRIEL MINDLIN

ECOLOGICAL INFORMATICS

ELSEVIER SCIENCE BV

Año: 2023 vol. 78

1574-9541

Audio-based analysis of bird songs has proven to be a valuable practice for the growth of knowledge in the fieldsof ethology and ecology. In recent years, machine learning techniques applied to audio field recordings of birdcalls have yielded successful results in studying population distributions and identification of individuals for theirmonitoring in a variety of bird species. This offers promising possibilities in the study of social behavior,biodiversity, and conservation strategies for birds. In this work, we trained deep learning models, directly fromthe sonograms of audio field recordings, to investigate the statistical properties of vocalizations in an endangeredbird species, the Yellow Cardinal, Gubernatrix cristata. This research marks the first successful application of thismethod to an endangered species. Our results indicate the presence of vocal signatures that reflect similarities insongs of individuals that inhabit the same region, determining dialects, but which also show differences betweenindividuals. These differences can be exploited by a deep learning classifier to discriminate the bird identitiesthrough their songs. Models trained with data labeled by regions showed a good performance in the recognitionof dialects with a mean accuracy of 0.84 ± 0.04, significantly higher than the accuracy obtained by chance.Precision and recall values also reflected the classifier’s ability to find alike vocal patterns in the songs ofneighboring individuals. Models trained with data labeled by individuals showed an accuracy of 0.63 ± 0.03,significantly higher than that obtained by chance. However, the individual discrimination model showed greaterconfusion with neighboring individuals. This reflects a hierarchical structure in the characteristics of the YellowCardinal’s vocalization, where the intra-individual variability is lower than the inter-individual variability, but itis even lower than the variability obtained when individuals inhabit different regions, providing evidence of theexistence of dialects. This reinforces the results of previous works but also offers an automated method forcharacterizing cultural units within the species. Along with genetic data, this method could help better definemanagement units, thereby benefiting the success of reintroduction of individuals of Yellow Cardinal recoveredfrom the illegal trade. Moreover, the novelty of individual discrimination using neural networks for the YellowCardinal, which has limited data availability, shows promise for non-invasive acoustic monitoring strategies withpotentially relevant implications for its conservation.