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

arXiv: https://arxiv.org/abs/2608.14824 · HTML: https://mlsanity.com/paper/2608.14824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 20 of 20)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [BEATs: Audio Pre-Training with Acoustic Tokenizers](https://mlsanity.com/paper/2212.09058/) (2022)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Contrastive Learning of General-Purpose Audio Representations](https://mlsanity.com/paper/2010.10915/) (2020)
- [Computational bioacoustics with deep learning: a review and roadmap](https://mlsanity.com/paper/2112.06725/) (2021)
- [Global birdsong embeddings enable superior transfer learning for bioacoustic classification](https://mlsanity.com/paper/2307.06292/) (2023)
- [BEANS: The Benchmark of Animal Sounds](https://mlsanity.com/paper/2210.12300/) (2022)
- [Perch 2.0: The Bittern Lesson for Bioacoustics](https://mlsanity.com/paper/2508.04665/) (2025)
- [Learning to detect an animal sound from five examples](https://mlsanity.com/paper/2305.13210/) (2023)
- [Few-shot bioacoustic event detection at the DCASE 2022 challenge](https://mlsanity.com/paper/2207.07911/) (2022)
- [Perch 2.0 transfers 'whale' to underwater tasks](https://mlsanity.com/paper/2512.03219/) (2025)
- [Automatic Detection and Compression for Passive Acoustic Monitoring of the African Forest Elephant](https://mlsanity.com/paper/1902.09069/) (2019)
- [Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds](https://mlsanity.com/paper/2509.04166/) (2025)
- [Few-shot bioacoustic event detection at the DCASE 2023 challenge](https://mlsanity.com/paper/2306.09223/) (2023)
- [Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures](https://mlsanity.com/paper/2410.12082/) (2024)
- [Elephants and Algorithms: A Review of the Current and Future Role of AI in Elephant Monitoring](https://mlsanity.com/paper/2306.13803/) (2023)
- [From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings](https://mlsanity.com/paper/2605.00225/) (2026)

## Abstract (arXiv)

We present a parameter-free episodic evaluation of nearest-centroid classification of elephant vocalisations on fixed pretrained embeddings, for the Elephant Voices (EV) and Linguistic Data Consortium (LDC) datasets. We ask not which embedding yields the best classifier trained on all labelled data, but how the simplest classifier performs as the number of exemplars per class varies. There are no learnable parameters, because each class is modelled as the mean of its support embeddings and each query is assigned to the nearest centroid under squared Euclidean distance. Evaluation covers the fixed Perch (ver. 1), Perch (ver. 2) and HuBERT (base, layer 2) embeddings, alongside mel frequency cepstral coefficient (MFCC) features, N-way k-shot, under the same stratified K-fold cross-validation protocol as the trained classifiers. None of these embedding models was trained to distinguish elephant call types. On the smaller EV dataset the centroid classifier is markedly data-efficient. Using Perch (ver. 1) or Perch (ver. 2) embeddings it overtakes in mean average precision (mAP) the fully-trained logistic regression (LR) baseline from one or two exemplars and the recurrent baseline from two. Over the reduced set of call types on which the strongly-supervised end-to-end baseline was trained, the centroid classifier using Perch (ver. 2) embeddings overtakes that baseline in mAP as well, from two exemplars. On the larger LDC dataset the recurrent baselines retain their advantage for all considered values of k. Only LR is overtaken, and only in mAP. Nearest-centroid classification is therefore preferable precisely when exemplars are few and the fixed embedding already separates the call types.