Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire
Although there is a growing number of researches focusing on acoustic communication, the lack of shared analytic approaches leads to inconsistency among studies. Here, we introduced a computational method used to examine 3360 calls recorded from wild indris (<i>Indri indri</i>) from 2005...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-05-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/9/5/243 |
| _version_ | 1819146786043854848 |
|---|---|
| author | Daria Valente Chiara De Gregorio Valeria Torti Longondraza Miaretsoa Olivier Friard Rose Marie Randrianarison Cristina Giacoma Marco Gamba |
| author_facet | Daria Valente Chiara De Gregorio Valeria Torti Longondraza Miaretsoa Olivier Friard Rose Marie Randrianarison Cristina Giacoma Marco Gamba |
| author_sort | Daria Valente |
| collection | DOAJ |
| description | Although there is a growing number of researches focusing on acoustic communication, the lack of shared analytic approaches leads to inconsistency among studies. Here, we introduced a computational method used to examine 3360 calls recorded from wild indris (<i>Indri indri</i>) from 2005–2018. We split each sound into ten portions of equal length and, from each portion we extracted spectral coefficients, considering frequency values up to 15,000 Hz. We submitted the set of acoustic features first to a t-distributed stochastic neighbor embedding algorithm, then to a hard-clustering procedure using a k-means algorithm. The t-distributed stochastic neighbor embedding (t-SNE) mapping indicated the presence of eight different groups, consistent with the acoustic structure of the a priori identification of calls, while the cluster analysis revealed that an overlay between distinct call types might exist. Our results indicated that the t-distributed stochastic neighbor embedding (t-SNE), successfully been employed in several studies, showed a good performance also in the analysis of indris’ repertoire and may open new perspectives towards the achievement of shared methodical techniques for the comparison of animal vocal repertoires. |
| first_indexed | 2024-12-22T13:19:27Z |
| format | Article |
| id | doaj.art-c6fcc34c2c2c4c45b64b7100e08594c5 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-12-22T13:19:27Z |
| publishDate | 2019-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-c6fcc34c2c2c4c45b64b7100e08594c52022-12-21T18:24:30ZengMDPI AGAnimals2076-26152019-05-019524310.3390/ani9050243ani9050243Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal RepertoireDaria Valente0Chiara De Gregorio1Valeria Torti2Longondraza Miaretsoa3Olivier Friard4Rose Marie Randrianarison5Cristina Giacoma6Marco Gamba7Dipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyDipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyDipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyDipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyDipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyGroup d’Etude et de Recherche sur les Primates de Madagascar, Antananarivo 101, MadagascarDipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyDipartimento di Scienze della Vita e Biologia dei Sistemi, Università degli Studi di Torino, 10123 Torino, ItalyAlthough there is a growing number of researches focusing on acoustic communication, the lack of shared analytic approaches leads to inconsistency among studies. Here, we introduced a computational method used to examine 3360 calls recorded from wild indris (<i>Indri indri</i>) from 2005–2018. We split each sound into ten portions of equal length and, from each portion we extracted spectral coefficients, considering frequency values up to 15,000 Hz. We submitted the set of acoustic features first to a t-distributed stochastic neighbor embedding algorithm, then to a hard-clustering procedure using a k-means algorithm. The t-distributed stochastic neighbor embedding (t-SNE) mapping indicated the presence of eight different groups, consistent with the acoustic structure of the a priori identification of calls, while the cluster analysis revealed that an overlay between distinct call types might exist. Our results indicated that the t-distributed stochastic neighbor embedding (t-SNE), successfully been employed in several studies, showed a good performance also in the analysis of indris’ repertoire and may open new perspectives towards the achievement of shared methodical techniques for the comparison of animal vocal repertoires.https://www.mdpi.com/2076-2615/9/5/243lemursvocal communicationunsupervised analyses |
| spellingShingle | Daria Valente Chiara De Gregorio Valeria Torti Longondraza Miaretsoa Olivier Friard Rose Marie Randrianarison Cristina Giacoma Marco Gamba Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire Animals lemurs vocal communication unsupervised analyses |
| title | Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire |
| title_full | Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire |
| title_fullStr | Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire |
| title_full_unstemmed | Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire |
| title_short | Finding Meanings in Low Dimensional Structures: Stochastic Neighbor Embedding Applied to the Analysis of <i>Indri indri</i> Vocal Repertoire |
| title_sort | finding meanings in low dimensional structures stochastic neighbor embedding applied to the analysis of i indri indri i vocal repertoire |
| topic | lemurs vocal communication unsupervised analyses |
| url | https://www.mdpi.com/2076-2615/9/5/243 |
| work_keys_str_mv | AT dariavalente findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT chiaradegregorio findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT valeriatorti findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT longondrazamiaretsoa findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT olivierfriard findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT rosemarierandrianarison findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT cristinagiacoma findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire AT marcogamba findingmeaningsinlowdimensionalstructuresstochasticneighborembeddingappliedtotheanalysisofiindriindriivocalrepertoire |