A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification

[2608.14824] A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2608.14824 (eess) [Submitted on 14 Aug 2026] Title: A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification Authors: Christiaan M. Geldenhuys , Thomas R. Niesler View a PDF of the paper titled A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification, by Christiaan M. Geldenhuys and 1 other authors View PDF HTML (experimental) Abstract: We present a parameter-free episodic evaluation of nearest-centroid classification for elephant vocalisations on fixed pretrained acoustic embeddings, across the Elephant Voices (EV) and Linguistic Data Consortium (LDC) datasets. Rather than asking which embedding yields the best classifier when trained on all available labelled data, we ask how the simplest classifier performs as labelled exemplars per class are varied. Each class is represented by the mean of its support-set embeddings, and each query is assigned to the nearest centroid under squared Euclidean distance. We evaluate this centroid classifier on the Perch (ver. 1), Perch (ver. 2), and HuBERT (base, layer 2) embeddings, together with mel frequency cepstral coefficient (MFCC) features, in an N-way k-shot manner under the same cross-validation protocol as the trained baselines. A bootstrap over 100 resampled support sets quantifies the sampling noise. On the smaller, low-resource EV dataset, the centroid classifier using the stronger Perch (ver. 1) and Perch (ver. 2) embeddings overtakes the fully-trained logistic regression classifier from a single exemplar per class and the stronger recurrent classifier from two. Over the reduced set of call types on which the strongly-supervised end-to-end baseline was trained, the centroid classifier matches and then surpasses that baseline in mean average precision (mAP), from a few exemplars per class. On the larger LDC dataset, where labelled exemplars are abundant, the trained baselines retain their advantage at every k considered. At five exemplars per class, the centroid classifier using the strongest embedding, Perch (ver. 2), attains a mAP of 0.542 on the EV dataset and 0.368 on the LDC dataset. Parameter-free nearest-centroid classification is the stronger choice when labelled exemplars are few and the fixed embedding already encodes the features that separate the call types. Subjects: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG); Sound (cs.SD); Quantitative Methods (q-bio.QM) Cite as: arXiv:2608.14824 [eess.AS] (or arXiv:2608.14824v1 [eess.AS] for this version) https://doi.org/10.48550/arXiv.2608.14824 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Christiaan Geldenhuys [ view email ] [v1] Fri, 14 Aug 2026 18:54:24 UTC (648 KB) Full-text links: Access Paper: View a PDF of the paper titled A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification, by Christiaan M. Geldenhuys and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: eess.AS < prev | next > new | recent | 2026-08 Change to browse by: cs cs.LG cs.SD eess q-bio q-bio.QM References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Acoustic detection of a rarely vocalising invasive mammal from sparse data#390857
• Improving the sensitivity of liver tumor classification in ultrasound images <i>via</i> a power-law shot noise model#69718
• Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification#1035558
• Adaptation of Speech and Bioacoustics Models#442454
• Inter-Speaker Relative Cues for Two-Stage Text-Guided Target Speech Extraction#1051451