Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification
Abstract
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, restricting their usable bandwidth to the 0-8 kHz baseband and discarding higher-frequency information present in many bioacoustic recordings. We investigate a multi-band encoding framework that decomposes the full spectrum of animal calls into band features and fuses them into a unified representation. Similarity analyses on models show that certain encoders produce decorrelated band embeddings that improve class separation after fusion. Classification experiments on three bioacoustic datasets using eight pre-trained models and five fusion strategies show that fused representations consistently outperform the baseband and time-expansion baselines on two datasets, showing the potential of multi-band methods for full-spectrum encoding of animal calls.
Cite
@article{arxiv.2604.27936,
title = {Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification},
author = {Eklavya Sarkar and Marius Miron and David Robinson and Gagan Narula and Milad Alizadeh and Ellen Gilsenan-McMahon and Emmanuel Chemla and Olivier Pietquin and Matthieu Geist},
journal= {arXiv preprint arXiv:2604.27936},
year = {2026}
}