Abstract
Previous studies have applied Artificial Neural Networks (ANNs) successfully to bioacoustic problems at different levels of analysis (individual and species identification, vocal repertoire categorization, and analysis of sound structure) but not to nonhuman primates. Here, we report the results of applying this tool to two important problems in primate vocal communication. First, we apply a supervised ANN to classify 222 long grunt vocalizations emitted by five species of the genus Eulemur. Second, we use an unsupervised self-organizing network to identify discrete categories within the vocal repertoire of black lemurs (Eulemur macaco). Calls were characterized by both spectral (fundamental frequency and formants) and temporal features. The result show not only that ANNs are effective for studying primate vocalizations but also that this tool can increase the efficiency, objectivity, and biological significance of vocal classification greatly. The advantages of ANNs over more commonly used statistical techniques and different applications for supervised and unsupervised ANNs are discussed.
Resume
Des études antérieures ont appliqué avec succès les Réseaux Neuronaux Artificiels (RNA) aux questions bioacoustiques (reconnaissance individuelle et inter-spécifique, catégorisation des répertoires vocaux, et analyse des structures sonores), mais pas sur les primates non-humains. Ici nous appliquons cet outil à deux problèmes concernant la communication vocale des Primates. Premièrement, nous utilisons un modèle de RNA « supervisé » à la classification de 222 « grognements longs » émis par 5 espèces du genre Eulemur. Deuxièmement, nous utilisons un modèle auto-organisé « non supervisé » de RNA pour identifier des catégories discrètes dans le répertoire vocal du lémur Macaco (Eulemur macaco). Les vocalisations sont caractérisées par leurs propriétés spectrales (fréquence fondamentale et formant) et temporelles. Les résultats montrent que les RNA sont des outils efficaces pour l’étude des vocalisations des primates, mais aussi que cette méthode qui accroit l’efficacité, l’objectivité, et la signification biologique des classifications vocales. Les avantages des RNA sur d’autres méthodes communément utilisées, ainsi que différentes applications des RNA supervisées et non supervisées sont discutés.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adi K, Johnson MT, Osiejuk TS (2010) Acoustic censusing using automatic vocalization classification and identity recognition. J Acoust Soc Am 127:874–883
Campbell GS, Gisiner RC, Helweg DA, Milette LL (2002) Acoustic identification of female Steller sea lions (Eumetopias jubatus). J Acoust Soc Am 111:2920–2928
Chesmore D (2004) Automated bioacoustic identification of species. An Acad Bras Cienc 76:435–440
Chesmore ED, Ohya E (2004) Automated identification of field-recorded songs of four British grasshoppers using bioacoustic signal recognition. Bull Entomol Res 94:319–330
Dawson MR, Charrier I, Sturdy CB (2006) Using an artificial neural network to classify black-capped chickadee (Poecile atricapillus) call note types. J Acoust Soc Am 119:3161–3172
Demuth H, Beale M (1993) Neural network toolbox. The MathWorks, Inc., Natick, MA
Derégnaucourt S, Guyomarc’h J-C, Richard V (2001) Classification of hybrid crows in quail using artificial neural networks. Behav Proc 56:103–112
Gamba M, Giacoma C (2005) Key issues in the study of primate acoustic signals. J Anthropol Sci 83:61–87
Ghirlanda S, Enquist M (1998) Artificial neural networks as models of stimulus control. Anim Behav 56:1383–1389
Gosset D, Fornasieri I, Roeder J-J (2002) Acoustic structure and contexts of emission of vocal signals by black lemurs. Evol Commun 4:225–251
Green SR, Mercado E, Pack AA, Herman LM (2011) Recurring patterns in the songs of humpback whales (Megaptera novaeangliae). Behav Proc 86:284–294
Jennings N, Parsons S, Pocock MJO (2008) Human vs. machine: identification of bat species from their echolocation calls by humans and by artificial neural networks. Can J Zool 86:371–377
Kohonen T (1988) The ‘neural’ phonetic typewriter. Computer 21:11–22
Lopes MT, Gioppo LL, Higushi TT, Kaestner CAA, Silla Jr, CN, Koerich AL (2011) Automatic bird species identification for large number of species. IEEE international symposium on multimedia, pp. 117–122
Macedonia JM, Stanger KF (1994) Phylogeny of the Lemuridae revisited: evidence from communication signals. Folia Primatol 63:1–43
Mercado E, Kuh A (1998) Classification of humpback whale vocalizations using a self-organizing neural network. Proceedings of the 1998 IEEE joint conference on neural networks, pp 1584–1589. doi: 10.1109/IJCNN.1998.686014
Murray SO, Mercado E, Roitblat HL (1998) The neural network classification of false killer whale (Pseudorca crassidens) vocalizations. J Acoust Soc Am 104:3626–3633
Nickerson CM, Bloomfield LL, Dawson MR, Sturdy CB (2006) Artificial neural network discrimination of black-capped chickadee (Poecile atricapillus) call notes. J Acoust Soc Am 120:1111–1117
Parsons S (2001) Identification of New Zealand bats (Chalinolobus tuberculatus and Mystacina tuberculata) in flight from analysis of echolocation calls by artificial neural networks. J Zool 253:447–456
Placer J, Slobodchikoff CN (2000) A fuzzy-neural system for identification of species-specific alarm calls of Gunnison’s prairie dogs. Behav Proc 52:1–9
Pozzi L, Gamba M, Giacoma C (2010) The use of artificial neural networks to classify primate vocalizations: a pilot study on black lemurs. Am J Primatol 72:337–348
Reby D, Lek S, Dimopoulos I, Joachim J, Lauga J, Aulagnier S (1997) Artificial neural networks as a classification method in the behavioural sciences. Behav Proc 40:35–43
Zimmermann A (1995) Artificial neural networks for analysis and recognition of primate vocal communication. In: Zimmermann E, Newman JO, Jürgens UWE (eds) Current topics in primate vocal communication. Plenum, New York, pp 29–46
Acknowledgments
We thank Judith Masters for providing the opportunity to contribute to this volume. We also thank Cesare Avesani Zaborra and Parco Natura Viva for their continued support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Science+Business Media New York
About this chapter
Cite this chapter
Pozzi, L., Gamba, M., Giacoma, C. (2012). Artificial Neural Networks: A New Tool for Studying Lemur Vocal Communication. In: Masters, J., Gamba, M., Génin, F. (eds) Leaping Ahead. Developments in Primatology: Progress and Prospects. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-4511-1_34
Download citation
DOI: https://doi.org/10.1007/978-1-4614-4511-1_34
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-4510-4
Online ISBN: 978-1-4614-4511-1
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)