Rate-Agnostic Bioacoustics: Heterogeneous Multi-Taxa Classification with Continuous Filterbanks and Fourier Neural Operators

Stefano Ciapponi; Francesco Ardan Dal Rı; Nicola Conci; Elisabetta Farella

cs.SDSep 29, 2026

Rate-Agnostic Bioacoustics: Heterogeneous Multi-Taxa Classification with Continuous Filterbanks and Fourier Neural Operators

Authors: Stefano Ciapponi, Francesco Ardan Dal Rı, Nicola Conci, Elisabetta Farella

Organizations: University of Trento · Fondazione Bruno Kessler

Abstract

Conventional bioacoustic classification models rely on fixed-rate spectral representations, requiring recordings acquired at heterogeneous sampling rates to be resampled before analysis. We propose a Sampling-Frequency-Independent (SFI) frontend that processes each recording directly at its native sampling rate, coupled with a Fourier Neural Operator (FNO) backbone featuring progressive temporal-scale fusion. This framework avoids fixed-rate resampling and high-frequency information loss while producing fixed-size representations across sampling rates. Mild training-time sampling-rate (\textit{sr}) augmentation further improves robustness to unseen rate variations. Evaluated on a multi-taxa corpus comprising 84 classes and 60 sampling rates, the proposed SFI-FNO configuration outperforms fixed-rate and corpus-maximum-rate baselines, achieving .906 accuracy, .921 balanced accuracy, and a Macro-F1 score of .899.

Figures & tables

Figure 1 : Examples of different spectrograms for different taxa, emphasizing the large sample-rate variability.

Figure 2 : SFI multi-scale features applied to a Fringilla coelebs audio clip at native 24 kHz using 16, 64, and 256 ms scales.

Dataset	Classes	Samples/class	Rates	Rate (kHz)
Marine [ 20 ]	42	$362\pm 485$	43	$62.8\pm 49.8$
Birds [ 9 ]	10	$250\pm 0$	1	$24.0\pm 0.0$
Frogs [ 1 ]	26	$59\pm 14$	2	$48.0\pm 0.1$
Bats [ 17 ]	6	$198\pm 48$	19	$273.4\pm 108.5$
Total	84	$\mathbf{243\pm 368}$	60	$\mathbf{69.2\pm 72.6}$

Table 1: Corpora statistics (

\mu/\sigma

after class filtering).

Figure 3 : Number of files in the entire corpora for every individual native sample rate (log scale for better visualization).

Front.	Back.	Params.	Accuracy	Bal. Acc.	Macro-F1
MEL48	CNN	916,496	.831 $\pm$ .019	.881 $\pm$ .009	.847 $\pm$ .017
	MBC	854,532	.838 $\pm$ .019	.886 $\pm$ .009	.852 $\pm$ .016
	FNO	1,007,048	.860 $\pm$ .008	.893 $\pm$ .002	.866 $\pm$ .004
MAX	CNN	916,496	.860 $\pm$ .014	.894 $\pm$ .004	.865 $\pm$ .006
	MBC	854,532	.888 $\pm$ .008	.914 $\pm$ .009	.892 $\pm$ .010
	FNO	1,007,048	.895 $\pm$ .010	.910 $\pm$ .008	.890 $\pm$ .010

Table 2 : Classification results (reported as mean

\pm

std.)

Model	$95\%$	$90\%$	Rand. ( $85$ - $95\%$ )	Mean $\Delta$ F1
SFI-FNO	$.703\pm.031$	$.555\pm.024$	$.563\pm.025$	$-.291\pm.074$
SFI-FNO + aug.	$.865\pm.007$	.869 $\pm$ .007	.869 $\pm$ .006	$\mathbf{-.004\pm.005}$
MAX-FNO	.867 $\pm$ .011	$.851\pm.014$	$.855\pm.011$	$-.025\pm.016$

Table 3 : Macro-F1 under sr perturbation (mean

\pm

std.).

Dataset	Accuracy	Balanced Acc.	Macro F1
Marine [ 20 ]	$.933\pm.012$	$.942\pm.006$	$.903\pm.011$
Birds [ 9 ]	$.675\pm.030$	$.675\pm.030$	$.673\pm.029$
Frogs [ 1 ]	$.996\pm.004$	$.991\pm.004$	$.991\pm.004$
Bats [ 17 ]	$.866\pm.017$	$.859\pm.019$	$.863\pm.017$

Table 4 : Per-dataset performance of the SFI-FNO model, reported as mean

\pm

standard deviation over five folds.

Explore similar work

Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification
Apr 30, 2026Eklavya Sarkar, Marius Miron, David Robinson +6Passive Acoustic Monitoring Animal Vocalizations
Earth Species Project
Localized time-frequency representation learning for bioacoustic classification in complex soundscapes
Feb 19, 2025Simen Hexeberg, Mandar Chitre, Matthias Hoffmann-Kuhnt +1Passive Acoustic Monitoring Animal Vocalizations
ARL, Tropical Marine Science Institute, National University of Singapore · Department of Electrical & Computer Engineering, National University of Singapore · National Parks Board, Singapore
Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data
May 5, 2026Ragib Amin Nihal, Benjamin Yen, Runwu Shi +2Passive Acoustic Monitoring Classifier
Systems and Control Engineering, Institute of Science Tokyo, Japan · RIKEN BDR, Japan

Apr 30, 2026, cs.LGJ/K move · Enter open · S save

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

Eklavya Sarkar, Marius Miron, David Robinson, Gagan Narula+5

Earth Species Project

Passive Acoustic Monitoring Animal Vocalizations

Open paper AskPDF 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, 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.

Abstract

Explore similar work

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

Localized time-frequency representation learning for bioacoustic classification in complex soundscapes

Ecologically-Constrained Task Arithmetic for Multi-Taxa Bioacoustic Classifiers Without Shared Data