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

TL;DR

This paper introduces an adaptive multi-band encoding framework that leverages the full spectrum of bioacoustic signals, improving animal call classification over traditional baseband methods.

Contribution

It proposes a novel multi-band encoding and fusion approach that captures full-spectrum animal vocalizations, enhancing classification accuracy in bioacoustic analysis.

Findings

Fused multi-band representations outperform baseband models on multiple datasets.

Certain encoders produce decorrelated band embeddings that improve class separation.

The approach demonstrates the potential of full-spectrum encoding for bioacoustic 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.