mlsanityData to 7 Oct 2026

MetaAudio: A Few-Shot Audio Classification Benchmark

arXiv 2204.02121 ↗First posted 5 Apr 2022cs.SD cs.LG eess.AScited by 24

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 5 Apr 2022.

Builds on

17 of 23 references.

References · 17

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2016Matching Networks for One Shot Learningcited by 2,246
  4. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  5. 2021AST: Audio Spectrogram Transformercited by 634
  6. 2017Learning multiple visual domains with residual adapterscited by 553
  7. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 377
  8. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 339
  9. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  10. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  11. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  12. 2019Meta-Curvaturecited by 70
5 more
  1. 2021Few-Shot Learning with Class Imbalancecited by 18
  2. 2018Learning to match transient sound events using attentional similarity for few-shot sound recognitioncited by 13
  3. 2020Few-shot acoustic event detection via meta-learningcited by 13
  4. 2021A Channel Coding Benchmark for Meta-Learningcited by 6
  5. 2020A Study of Few-Shot Audio Classificationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 10; 2025: 5; 2026: 2.

24 papers.

Sort:

By area:

  1. 2024BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacousticscited by 36
  2. 2023Self-Supervised Learning for Few-Shot Bird Sound Classificationcited by 11
  3. 2023Amortised Invariance Learning for Contrastive Self-Supervisioncited by 8
  4. 2023Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detectioncited by 7
  5. 2024Synthio: Augmenting Small-Scale Audio Classification Datasets with Synthetic Datacited by 7
  6. 2024Mixture of Mixups for Multi-label Classification of Rare Anuran Soundscited by 4
  7. 2024Stepping Forward on the Last Milecited by 4
  8. 2023MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representationscited by 3
  9. 2023HalluAudio: Hallucinating Frequency as Concepts for Few-Shot Audio Classificationcited by 2
  10. 2023Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learningcited by 2
  11. 2023Pretraining Representations for Bioacoustic Few-shot Detection using Supervised Contrastive Learningcited by 2
  12. 2024On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classificationcited by 2
12 more
  1. 2024Meta-Learning in Audio and Speech Processing: An End to End Comprehensive Reviewcited by 2
  2. 2024Episodic fine-tuning prototypical networks for optimization-based few-shot learning: Application to audio classificationcited by 2
  3. 2025Prototypical Contrastive Learning For Improved Few-Shot Audio Classificationcited by 2
  4. 2026SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classificationcited by 2
  5. 2024EnvId: A Metric Learning Approach for Forensic Few-Shot Identification of Unseen Environmentscited by 0
  6. 2024A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognitioncited by 0
  7. 2024Transfer Learning in Vocal Education: Technical Evaluation of Limited Samples Describing Mezzo-sopranocited by 0
  8. 2025MCLRL: A Multi-Domain Contrastive Learning with Reinforcement Learning Framework for Few-Shot Modulation Recognitioncited by 0
  9. 2025A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domainscited by 0
  10. 2025Overcoming Labelled Data Scarcity for Defect Classification in Scanning Tunneling Microscopycited by 0
  11. 2025Episode-specific Fine-tuning for Metric-based Few-shot Learners with Optimization-based Trainingcited by 0
  12. 2026Sample-Conditioned Representation Selection for Audio Few-Shot Learningcited by 0