MetaAudio: A Few-Shot Audio Classification Benchmark

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.

Paper on arXiv
Paper on Springer
Code
Papers With Code Entry

Recommended citation (BibTex):” @InProceedings{10.1007/978-3-031-15919-0_19, author=”Heggan, Calum and Budgett, Sam and Hospedales, Timothy and Yaghoobi, Mehrdad”, editor=”Pimenidis, Elias and Angelov, Plamen and Jayne, Chrisina and Papaleonidas, Antonios and Aydin, Mehmet”, title=”MetaAudio: A Few-Shot Audio Classification Benchmark”, booktitle=”Artificial Neural Networks and Machine Learning – ICANN 2022”, year=”2022”, publisher=”Springer International Publishing”, address=”Cham”, pages=”219–230”, isbn=”978-3-031-15919-0” }”