Large-scale unsupervised clustering of Orca vocalizations: a model for describing Orca communication systems

• Main Authors: Poupard, Marion, Best, Paul, Schlüter, Jan, Symonds, Helena, Spong, Paul, Lengagne, Thierry, Soriano, Thierry, Glotin, Hervé
• Other Authors: Université de Toulon - UFR Sciences et Techniques (UTLN UFR ScT), Université de Toulon (UTLN), DYNamiques de l’Information (DYNI), Laboratoire d'Informatique et des Systèmes (LIS) (Marseille, Toulon) (LIS), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS)-Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Laboratoire d'Ecologie des Hydrosystèmes Naturels et Anthropisés (LEHNA), Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-École Nationale des Travaux Publics de l'État (ENTPE)-Centre National de la Recherche Scientifique (CNRS), Laboratoire Conception de Systèmes Mécaniques et Robotiques - EA 7398 (COSMER), ANR-20-CHIA-0014,ADSIL,Écoute intelligente sous-marine avancée(2020), ANR-18-CE40-0014,SMILES,Modélisation et Inférence Statistique pour l'Apprentissage non-supervisé à partir de Données Massives(2018)
• Format: Conference Object
• Language: English
• Published: HAL CCSD 2019
• Subjects: [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]; [PHYS.MECA.ACOU]Physics [physics]/Mechanics [physics]/Acoustics [physics.class-ph]; [SDV.EE]Life Sciences [q-bio]/Ecology; environment; Orca; Orcinus orca
• Online Access: https://hal.science/hal-02965872; https://hal.science/hal-02965872/document; https://hal.science/hal-02965872/file/poupard_best.pdf; https://doi.org/10.7287/peerj.preprints.27979v1

International audience Killer whales (Orcinus orca) can produce 3 types of signals: clicks, whistles and vocalizations. This study focuses on Orca vocalizations from northern Vancouver Island (Hanson Island) where the NGO Orcalab developed a multi-hydrophone recording station to study Orcas. The acoustic station is composed of 5 hydrophones and extends over 50 km 2 of ocean. Since 2015 we are continuously streaming the hydrophone signals to our laboratory in Toulon, France, yielding nearly 50 TB of synchronous multichannel recordings. In previous work, we trained a Convolutional Neural Network (CNN) to detect Orca vocalizations, using transfer learning from a bird activity dataset. Here, for each detected vocalization, we estimate the pitch contour (fundamental frequency). Finally, we cluster vocalizations by features describing the pitch contour. While preliminary, our results demonstrate a possible route towards automatic Orca call type classification. Furthermore, they can be linked to the presence of particular Orca pods in the area according to the classification of their call types. A large-scale call type classification would allow new insights on phonotactics and ethoacoustics of endangered Orca populations in the face of increasing anthropic pressure.