Figure 2

studied by magnetoencephalography. InAuditory signal processing(eds D Pressnitzer, A de Cheveigné, S McAdams, L Collet), pp. 154–161. New York, NY: Springer New York. (doi:10.1007/0-387-27045-0_19) 44.Poole JH. 2011 Behavioral contexts of e…

hales have different baseline coda durations. Fifth, the edge clicks of co‑ das sometimes match the adjacent codas, which is suggestive of coarticulation. Crucially, we report these properties in a culturally learnt animal communication sys…

=−3.07,p=0.002). Mismatched first clicks are also more frequent oni‑codas than ona‑codas. The preceding vowel does not have a significant effect on the rate of mismatched first clicks (i.e. there is no effect of whether the preceding vowel …

far the most common type produced by members of the EC1 clan and the only type that has enough instances of the two coda vowels. Additionally, we restricted our analysis to codas produced by four whales only. Atwood, Fork, Pinchy and TBB ea…

ded from http://royalsocietypublishing.org/rspb/article-pdf/doi/10.1098/rspb.2025.2994/6132512/rspb.2025.2994.pdf by guest on 12 June 2026 3 royalsocietypublishing.org/journal/rspb Proc. R. Soc. B 293: 20252994 ............................…

royalsocietypublishing.org/journal/rspb Research Cite this article:Beguš G, Dąbkowski M, Sprouse RL, Gruber DF, Gero S. 2026 The phonology of sperm whale coda vowels.Proc. R. Soc. B293: 20252994. https://doi.org/10.1098/rspb.2025.2994 Recei…

royalsocietypublishing.org/journal/rspb Research Cite this article:Beguš G, Dąbkowski M, Sprouse RL, Gruber DF, Gero S. 2026 The phonology of sperm whale coda vowels.Proc. R. Soc. B293: 20252994. https://doi.org/10.1098/rspb.2025.2994 Rec…

nighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv [cs.LG], Jan. 2020. E. Mercado and S. Handel. Understanding the structure of humpback whale songs (l). The Jo…

Marine Science, 11:1394695, 2024. J. A. Allen, E. C. Garland, C. Garrigue, R. A. Dunlop, and M. J. Noad. Song complexity is maintained during inter-population cultural transmission of humpback whale songs. Scientific reports, 12(1): 8999, 2…

atasets with thousands of classes can be high performing, even on out-of-domain down- stream tasks. Next, the ‘bittern lesson’ learned when training Perch 2.0 was that bird species classification in particular is a challenging su- pervision…

= 8k = 16k = 8 k = 16k = 8 k = 16 GMWM0.8900.9140.7640.8210.9360.9540.868* 0.917*0.8230.855 SurfPerch 0.9320.9470.8590.9030.9810.9840.7960.8990.982* 0.986* Perch 1.0 0.9580.9680.9010.9310.9770.9810.8360.9050.9580.970 Perch 2.0 0.9…

V2.348 kHz3.0102420.0MBirds, Frogs AVES-bio16 kHzVariable768 2 94.4MGeneral Audio BirdAVES (large)16 kHzVariable1024 3 315.4MGeneral Audio + Birds 4 Comparison models. As our goal is to provide guidance on which pretrained embedding models …

ludes new classes unseen by the models. The classes used in the NOAA PIPAN evaluation set include anthropomorphic noise, unknown whale species, and the following baleen whale species: common minke whale, humpback whale, sei whale, blue whal…

ained on log-mel spectrograms using a classification loss. Additionally, the model used a form of self-distillation and a self-supervised loss (in the form of source recording prediction) with the goal of producing strong embeddings that ar…

ion as new sounds are discovered while not having large amounts of human labeled data. Despite these challenges, passive acoustic monitoring is a critical tool for marine conservation and ecology (Fleishman et al., 2023), and discoveries ab…

Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind Abs…

monitoring. Ecol. Inform., 61(101236):101236, Mar. 2021. 6 J. Kaplan, S. McCandlish, T. Henighan, T. B. Brown, B. Chess, R. Child, S. Gray, A. Radford, J. Wu, and D. Amodei. Scaling laws for neural language models. arXiv [cs.LG], Jan. 2020…

e datasets with thousands of classes can be high performing, even on out-of-domain down- stream tasks. Next, the ‘bittern lesson’ learned when training Perch 2.0 was that bird species classification in particular is a challenging su- pervis…

ce on which pretrained embedding models should be used for agile modeling and transfer learning (with existing tools), we limit our comparisons to models supported in the Perch Hoplite Github repository 5 . We compare the performance of the…

l of producing strong embeddings that are linearly separable for a wide range of bioacoustics tasks. Embeddings from the Perch model have shown successful generalization to tasks other than species classification (e.g., individual identific…

Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind Abs…

Perch 2.0 transfers ‘whale’ to underwater tasks Andrea Burns ∗ Google DeepMind Lauren Harrell ∗ Google Research Bart van Merriënboer Google DeepMind Vincent Dumoulin Google DeepMind Jenny Hamer Google DeepMind Tom Denton Google DeepMind A…