English

MetaAudio: A Few-Shot Audio Classification Benchmark

Sound 2022-04-12 v2 Machine Learning Audio and Speech Processing

Abstract

Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.

Keywords

Cite

@article{arxiv.2204.02121,
  title  = {MetaAudio: A Few-Shot Audio Classification Benchmark},
  author = {Calum Heggan and Sam Budgett and Timothy Hospedales and Mehrdad Yaghoobi},
  journal= {arXiv preprint arXiv:2204.02121},
  year   = {2022}
}

Comments

9 pages with 1 figure and 2 main results tables. V1 Preprint

R2 v1 2026-06-24T10:38:18.926Z