# One-shot learning for acoustic identification of bird species in non-stationary environments

arXiv: https://arxiv.org/abs/2105.00202 · HTML: https://mlsanity.com/paper/2105.00202/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 1 May 2021.

## Builds on (most cited first, 4 of 4)

- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [Training neural audio classifiers with few data](https://mlsanity.com/paper/1810.10274/) (2018)
- [Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning](https://mlsanity.com/paper/1405.6524/) (2014)
- [Adaptive DCTNet for Audio Signal Classification](https://mlsanity.com/paper/1612.04028/) (2016)

## Built on by (most cited first, 1 of 1)

- [Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design](https://mlsanity.com/paper/2511.18163/) (2025)

## Abstract (arXiv)

This work introduces the one-shot learning paradigm in the computational bioacoustics domain. Even though, most of the related literature assumes availability of data characterizing the entire class dictionary of the problem at hand, that is rarely true as a habitat's species composition is only known up to a certain extent. Thus, the problem needs to be addressed by methodologies able to cope with non-stationarity. To this end, we propose a framework able to detect changes in the class dictionary and incorporate new classes on the fly. We design an one-shot learning architecture composed of a Siamese Neural Network operating in the logMel spectrogram space. We extensively examine the proposed approach on two datasets of various bird species using suitable figures of merit. Interestingly, such a learning scheme exhibits state of the art performance, while taking into account extreme non-stationarity cases.