Large-scale unsupervised clustering of Orca vocalizations: a model for describing Orca communication systems - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

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

Abstract

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.
Fichier principal
Vignette du fichier
poupard_best.pdf (299.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02965872 , version 1 (13-10-2020)

Identifiers

Cite

Marion Poupard, Paul Best, Jan Schlüter, Helena Symonds, Paul Spong, et al.. Large-scale unsupervised clustering of Orca vocalizations: a model for describing Orca communication systems. 2nd International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots, Aug 2019, Londres, United Kingdom. ⟨10.7287/peerj.preprints.27979v1⟩. ⟨hal-02965872⟩
838 View
620 Download

Altmetric

Share

Gmail Facebook X LinkedIn More