From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings

• URL: http://arxiv.org/abs/2605.00225v1
• Date: Thu, 30 Apr 2026 21:00:05 GMT
• Title: From Birdsong to Rumbles: Classifying Elephant Calls with Out-of-Species Embeddings
• Abstract summary: We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks.<n>The best-performing system is within 2.2 % of an end-to-end supervised elephant call classification system.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: We show that pretrained acoustic embeddings classify elephant vocalisations at a level approaching that of end-to-end supervised neural networks, without any fine-tuning of the embedding model. This result is of practical importance because annotated bioacoustic data are scarce and costly to obtain, leaving conventional supervised approaches prone to overfitting and to poor generalisation under domain shift. A broad range of embedding models drawn from general audio, speech, and bioacoustic domains is evaluated, all of which are either out-of-domain (containing no bioacoustic data) or out-of-species (containing no elephant call data). The embedding networks themselves remain fixed; only the lightweight downstream classifiers, which include a linear model and several small neural networks, are trained. Among the models considered, Perch 2.0 achieves the best cross-validated classification performance, attaining AUCs of 0.849 on African bush elephant (Loxodonta africana) calls and 0.936 on Asian elephant (Elephas maximus) calls, with Perch 1.0 close behind. The best-performing system is within 2.2 % of an end-to-end supervised elephant call classification system. A layerwise analysis of pretrained transformer encoders, considered as embedding models, shows that intermediate representations outperform final-layer outputs. The second layer of both wav2vec2.0 and HuBERT encodes sufficient information for effective elephant call classification; truncation at this layer therefore preserves classification performance whilst retaining only approximately 10 % of the parameters of the full network. Such compact embedding networks are well suited to on-device processing where computational resources are limited.

Related papers

• Representation-Regularized Convolutional Audio Transformer for Audio Understanding [53.092757178419355]
  bootstrapping representations from scratch is computationally expensive, often requiring extensive training to converge.<n>We propose the Convolutional Audio Transformer (CAT), a unified framework designed to address these challenges.
  arXiv  Detail & Related papers  (2026-01-29T12:16:19Z)
• Learning to rumble: Automated elephant call classification, detection and endpointing using deep architectures [0.0]
  We consider the problem of detecting, isolating and classifying elephant calls in continuously recorded audio. For experimentation, we employ two annotated datasets, one containing Asian and the other African elephant vocalisations. We show that the current best performance can be improved by using an audio spectrogram transformer (AST), a neural architecture which has not been used for this purpose before, and which we have configured in a novel sequence-to-sequence manner. We conclude that a fully-automated elephant call detection and subcall classification system is within reach.
  arXiv  Detail & Related papers  (2024-10-15T21:56:40Z)
• Music Genre Classification using Large Language Models [50.750620612351284]
  This paper exploits the zero-shot capabilities of pre-trained large language models (LLMs) for music genre classification. The proposed approach splits audio signals into 20 ms chunks and processes them through convolutional feature encoders. During inference, predictions on individual chunks are aggregated for a final genre classification.
  arXiv  Detail & Related papers  (2024-10-10T19:17:56Z)
• Advanced Framework for Animal Sound Classification With Features Optimization [35.2832738406242]
  We propose an automated classification framework applicable to general animal sound classification. Our approach consistently outperforms baseline methods by over 25% in precision, recall, and accuracy.
  arXiv  Detail & Related papers  (2024-07-03T18:33:47Z)
• Towards small and accurate convolutional neural networks for acoustic biodiversity monitoring [0.0]
  CNNs are fast at inference time and achieve good classification performance. Recordings from a rainforest ecosystem were used. RF duration was a major driver of classification performance.
  arXiv  Detail & Related papers  (2023-12-06T18:34:01Z)
• Improving Primate Sounds Classification using Binary Presorting for Deep Learning [6.044912425856236]
  In this work, we introduce a generalized approach that first relabels subsegments of MEL spectrogram representations. For both the binary pre-sorting and the classification, we make use of convolutional neural networks (CNN) and various data-augmentation techniques. We showcase the results of this approach on the challenging textitComparE 2021 dataset, with the task of classifying between different primate species sounds.
  arXiv  Detail & Related papers  (2023-06-28T09:35:09Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Training Classifiers that are Universally Robust to All Label Noise Levels [91.13870793906968]
  Deep neural networks are prone to overfitting in the presence of label noise. We propose a distillation-based framework that incorporates a new subcategory of Positive-Unlabeled learning. Our framework generally outperforms at medium to high noise levels.
  arXiv  Detail & Related papers  (2021-05-27T13:49:31Z)
• Deep CNNs for large scale species classification [1.52292571922932]
  Methods utilizing dataset pruning and transfer learning are shown to outperform models trained without either of the two techniques. The ResNext based classification achieves a top-one validation error of 0.68 when classifying amongst the 1,010 species.
  arXiv  Detail & Related papers  (2021-02-03T03:53:03Z)
• Solving Long-tailed Recognition with Deep Realistic Taxonomic Classifier [68.38233199030908]
  Long-tail recognition tackles the natural non-uniformly distributed data in realworld scenarios. While moderns perform well on populated classes, its performance degrades significantly on tail classes. Deep-RTC is proposed as a new solution to the long-tail problem, combining realism with hierarchical predictions.
  arXiv  Detail & Related papers  (2020-07-20T05:57:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.