# Few-shot bioacoustic event detection at the DCASE 2023 challenge

arXiv: https://arxiv.org/abs/2306.09223 · HTML: https://mlsanity.com/paper/2306.09223/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 15 Jun 2023.

## Builds on (most cited first, 5 of 5)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Learning to detect an animal sound from five examples](https://mlsanity.com/paper/2305.13210/) (2023)
- [Few-shot bioacoustic event detection at the DCASE 2022 challenge](https://mlsanity.com/paper/2207.07911/) (2022)
- [Surrey System for DCASE 2022 Task 5: Few-shot Bioacoustic Event Detection with Segment-level Metric Learning](https://mlsanity.com/paper/2207.10547/) (2022)
- [Detailed temporal structure of communication networks in groups of songbirds](https://mlsanity.com/paper/1601.05449/) (2016)

## Built on by (most cited first, 3 of 3)

- [Mixture of Mixups for Multi-label Classification of Rare Anuran Sounds](https://mlsanity.com/paper/2403.09598/) (2024)
- [Multitask frame-level learning for few-shot sound event detection](https://mlsanity.com/paper/2403.11091/) (2024)
- [A Parameter-Free Few-Shot Evaluation for Elephant Vocalisation Classification](https://mlsanity.com/paper/2608.14824/) (2026)

## Abstract (arXiv)

Few-shot bioacoustic event detection consists in detecting sound events of specified types, in varying soundscapes, while having access to only a few examples of the class of interest. This task ran as part of the DCASE challenge for the third time this year with an evaluation set expanded to include new animal species, and a new rule: ensemble models were no longer allowed. The 2023 few shot task received submissions from 6 different teams with F-scores reaching as high as 63% on the evaluation set. Here we describe the task, focusing on describing the elements that differed from previous years. We also take a look back at past editions to describe how the task has evolved. Not only have the F-score results steadily improved (40% to 60% to 63%), but the type of systems proposed have also become more complex. Sound event detection systems are no longer simple variations of the baselines provided: multiple few-shot learning methodologies are still strong contenders for the task.