Projects per year
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.
|Title of host publication||Artificial Neural Networks and Machine Learning – ICANN 2022|
|Subtitle of host publication||31st International Conference on Artificial Neural Networks, Bristol, UK, September 6–9, 2022, Proceedings, Part I|
|Number of pages||12|
|Publication status||Published - 7 Sep 2022|
|Name||Lecture Notes in Computer Science|
FingerprintDive into the research topics of 'MetaAudio: A Few-Shot Audio Classification Benchmark'. Together they form a unique fingerprint.
- 2 Active
Anomaly Detection and Characterisation with Few-Shot Machine Learning
UK industry, commerce and public corporations
1/10/20 → 30/09/24
Signal Processing in the Information Age
Davies, M., Hopgood, J., Hospedales, T., Mulgrew, B., Thompson, J., Tsaftaris, S. & Yaghoobi Vaighan, M.
1/07/18 → 31/03/24