Cargando…

Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers

With their highly social nature and complex vocal communication system, marmosets are important models for comparative studies of vocal communication and, eventually, language evolution. However, our knowledge about marmoset vocalizations predominantly originates from playback studies or vocal inter...

Descripción completa

Detalles Bibliográficos
Autores principales: Phaniraj, Nikhil, Wierucka, Kaja, Zürcher, Yvonne, Burkart, Judith M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Royal Society 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10581777/
https://www.ncbi.nlm.nih.gov/pubmed/37848054
http://dx.doi.org/10.1098/rsif.2023.0399
_version_ 1785122201348866048
author Phaniraj, Nikhil
Wierucka, Kaja
Zürcher, Yvonne
Burkart, Judith M.
author_facet Phaniraj, Nikhil
Wierucka, Kaja
Zürcher, Yvonne
Burkart, Judith M.
author_sort Phaniraj, Nikhil
collection PubMed
description With their highly social nature and complex vocal communication system, marmosets are important models for comparative studies of vocal communication and, eventually, language evolution. However, our knowledge about marmoset vocalizations predominantly originates from playback studies or vocal interactions between dyads, and there is a need to move towards studying group-level communication dynamics. Efficient source identification from marmoset vocalizations is essential for this challenge, and machine learning algorithms (MLAs) can aid it. Here we built a pipeline capable of plentiful feature extraction, meaningful feature selection, and supervised classification of vocalizations of up to 18 marmosets. We optimized the classifier by building a hierarchical MLA that first learned to determine the sex of the source, narrowed down the possible source individuals based on their sex and then determined the source identity. We were able to correctly identify the source individual with high precisions (87.21%–94.42%, depending on call type, and up to 97.79% after the removal of twins from the dataset). We also examine the robustness of identification across varying sample sizes. Our pipeline is a promising tool not only for source identification from marmoset vocalizations but also for analysing vocalizations of other species.
format Online
Article
Text
id pubmed-10581777
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher The Royal Society
record_format MEDLINE/PubMed
spelling pubmed-105817772023-10-18 Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers Phaniraj, Nikhil Wierucka, Kaja Zürcher, Yvonne Burkart, Judith M. J R Soc Interface Life Sciences–Mathematics interface With their highly social nature and complex vocal communication system, marmosets are important models for comparative studies of vocal communication and, eventually, language evolution. However, our knowledge about marmoset vocalizations predominantly originates from playback studies or vocal interactions between dyads, and there is a need to move towards studying group-level communication dynamics. Efficient source identification from marmoset vocalizations is essential for this challenge, and machine learning algorithms (MLAs) can aid it. Here we built a pipeline capable of plentiful feature extraction, meaningful feature selection, and supervised classification of vocalizations of up to 18 marmosets. We optimized the classifier by building a hierarchical MLA that first learned to determine the sex of the source, narrowed down the possible source individuals based on their sex and then determined the source identity. We were able to correctly identify the source individual with high precisions (87.21%–94.42%, depending on call type, and up to 97.79% after the removal of twins from the dataset). We also examine the robustness of identification across varying sample sizes. Our pipeline is a promising tool not only for source identification from marmoset vocalizations but also for analysing vocalizations of other species. The Royal Society 2023-10-18 /pmc/articles/PMC10581777/ /pubmed/37848054 http://dx.doi.org/10.1098/rsif.2023.0399 Text en © 2023 The Authors. https://creativecommons.org/licenses/by/4.0/Published by the Royal Society under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, provided the original author and source are credited.
spellingShingle Life Sciences–Mathematics interface
Phaniraj, Nikhil
Wierucka, Kaja
Zürcher, Yvonne
Burkart, Judith M.
Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
title Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
title_full Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
title_fullStr Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
title_full_unstemmed Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
title_short Who is calling? Optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
title_sort who is calling? optimizing source identification from marmoset vocalizations with hierarchical machine learning classifiers
topic Life Sciences–Mathematics interface
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10581777/
https://www.ncbi.nlm.nih.gov/pubmed/37848054
http://dx.doi.org/10.1098/rsif.2023.0399
work_keys_str_mv AT phanirajnikhil whoiscallingoptimizingsourceidentificationfrommarmosetvocalizationswithhierarchicalmachinelearningclassifiers
AT wieruckakaja whoiscallingoptimizingsourceidentificationfrommarmosetvocalizationswithhierarchicalmachinelearningclassifiers
AT zurcheryvonne whoiscallingoptimizingsourceidentificationfrommarmosetvocalizationswithhierarchicalmachinelearningclassifiers
AT burkartjudithm whoiscallingoptimizingsourceidentificationfrommarmosetvocalizationswithhierarchicalmachinelearningclassifiers