# Who calls the shots? Rethinking Few-Shot Learning for Audio

arXiv: https://arxiv.org/abs/2110.09600 · HTML: https://mlsanity.com/paper/2110.09600/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2021.

## Built on by (most cited first, 11 of 11)

- [Conditional Generation of Audio from Video via Foley Analogies](https://mlsanity.com/paper/2304.08490/) (2023)
- [BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics](https://mlsanity.com/paper/2403.10380/) (2024)
- [Urban Rhapsody: Large-scale exploration of urban soundscapes](https://mlsanity.com/paper/2205.13064/) (2022)
- [MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations](https://mlsanity.com/paper/2305.17191/) (2023)
- [Characterizing Continual Learning Scenarios and Strategies for Audio Analysis](https://mlsanity.com/paper/2407.00465/) (2024)
- [Pretraining Representations for Bioacoustic Few-shot Detection using Supervised Contrastive Learning](https://mlsanity.com/paper/2309.00878/) (2023)
- [Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Review](https://mlsanity.com/paper/2408.10330/) (2024)
- [Representation Learning for the Automatic Indexing of Sound Effects Libraries](https://mlsanity.com/paper/2208.09096/) (2022)
- [Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations](https://mlsanity.com/paper/2305.02382/) (2023)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)
- [SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification](https://mlsanity.com/paper/2608.25054/) (2026)

## Abstract (arXiv)

Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set. While the field has seen notable advances in recent years, they have often focused on multi-class image classification. Audio, in contrast, is often multi-label due to overlapping sounds, resulting in unique properties such as polyphony and signal-to-noise ratios (SNR). This leads to unanswered questions concerning the impact such audio properties may have on few-shot learning system design, performance, and human-computer interaction, as it is typically up to the user to collect and provide inference-time support set examples. We address these questions through a series of experiments designed to elucidate the answers to these questions. We introduce two novel datasets, FSD-MIX-CLIPS and FSD-MIX-SED, whose programmatic generation allows us to explore these questions systematically. Our experiments lead to audio-specific insights on few-shot learning, some of which are at odds with recent findings in the image domain: there is no best one-size-fits-all model, method, and support set selection criterion. Rather, it depends on the expected application scenario. Our code and data are available at https://github.com/wangyu/rethink-audio-fsl.