paper-with-me

Papers

Beyond task performance: Decoding bioacoustic embeddings with speech features

2026-06-12 · Ines Nolasco, Jules Cauzinille, Marius Miron, Gagan Narula, Milad Alizadeh, Emmanuel Fernandez, Matthieu Geist, Ellen Gilsenan-McMahon, Olivier Pietquin, Emmanuel Chemla, Sara Keen arxiv

Pretrained audio embeddings are standard in bioacoustics, yet little is known about which acoustic features these models encode, nor which are useful for a given task. This hinders transparency and limits extension to rare species or data-scarce domains. Here we reveal which speech-like features are encoded in bioacoustic representations. Using the 88~eGeMAPS features across six taxonomic groups, we apply linear and nonlinear regression probes to quantify which acoustic properties each model captures. Results confirm a ``no free lunch'' pattern: no single model captures the full feature space. A concatenated embedding achieves the highest performance, suggesting complementary acoustic space coverage across models. Loudness features are best encoded ($R^2 = 0.76$) while F0 is hardest to recover ($R^2 = 0.33$). By cross-referencing recoverability with per-species feature salience (NMI), we derive data-driven model selection guidance for bioacoustics.

📄 PDF Abstract BibTeX arXiv:2606.14662

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier

2026-06-11 · Olga Isupova, Danil Kuzin, Ella Browning, Tom Mills 외 arxiv

Passive acoustic monitoring holds great promise for ecological inference, yet existing automated tools are typically narrowly trained and non-transferable. We address these limitations with PULSE, a semi-supervised, mult…

Self-Supervised LearningKnowledge DistillationActive Learning

Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification

2026-04-30 · Eklavya Sarkar, Marius Miron, David Robinson, Gagan Narula 외 arxiv

Animals hear and vocalize across frequency ranges that differ substantially from humans, often extending into the ultrasonic domain. Yet most computational bioacoustics systems rely on audio models pre-trained at 16 kHz,…

No Free Lunch from Audio Pretraining in Bioacoustics: A Benchmark Study of Embeddings

2025-08-13 · Chenggang Chen, Zhiyu Yang arxiv

Bioacoustics, the study of animal sounds, offers a non-invasive method to monitor ecosystems. Extracting embeddings from audio-pretrained deep learning (DL) models without fine-tuning has become popular for obtaining bio…

Perch 2.0: The Bittern Lesson for Bioacoustics

2025-08-06 · Bart van Merriënboer, Vincent Dumoulin, Jenny Hamer, Lauren Harrell 외 arxiv

Perch is a performant pre-trained model for bioacoustics. It was trained in supervised fashion, providing both off-the-shelf classification scores for thousands of vocalizing species as well as strong embeddings for tran…

Transfer Learning

Global birdsong embeddings enable superior transfer learning for bioacoustic classification

2023-07-12 · Burooj Ghani, Tom Denton, Stefan Kahl, Holger Klinck

Automated bioacoustic analysis aids understanding and protection of both marine and terrestrial animals and their habitats across extensive spatiotemporal scales, and typically involves analyzing vast collections of acou…

Audio ClassificationDecision MakingTransfer Learning