Bioacoustic classification works across multiple sampling rates accurately
Rate-Agnostic Bioacoustics: Heterogeneous Multi-Taxa Classification with Continuous Filterbanks and Fourier Neural Operators
Sound
Summary
Audio recordings of animal sounds often come in different quality levels, which makes it hard for computers to understand them if they rely on a fixed format. The authors developed a system that can learn to identify animal species from their sounds no matter how the recordings were made. Their method processes each recording in its original quality and combines information over time in a smart way. This approach was tested on a large and varied collection of animal sounds and performed better than standard methods that require changing the audio format first.
What this means in practice
- •For wildlife monitoring teams: Identify animal species from audio recordings recorded at different sampling qualities without resampling preprocessing delays.
- •For environmental sensor manufacturers: Build bioacoustic devices that can analyze sounds directly at their native recording rates for more accurate species detection.$Commercial implications: Enables production of smarter bioacoustic sensors that handle heterogeneous data seamlessly, improving market appeal for ecological monitoring products.
Authors
Stefano Ciapponi, Francesco Ardan Dal Rı, Nicola Conci, Elisabetta Farella
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.