mlsanityData to 7 Oct 2026

On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting

arXiv 2204.00352 ↗First posted 1 Apr 2022cs.LG eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

User-defined keyword spotting is a task to detect new spoken terms defined by users. This can be viewed as a few-shot learning problem since it is unreasonable for users to define their desired keywords by providing many examples. To solve this problem, previous works try to incorporate self-supervised learning models or apply meta-learning algorithms. But it is unclear whether self-supervised learning and meta-learning are complementary and which combination of the two types of approaches is most effective for few-shot keyword discovery. In this work, we systematically study these questions by utilizing various self-supervised learning models and combining them with a wide variety of meta-learning algorithms. Our result shows that HuBERT combined with Matching network achieves the best result and is robust to the changes of few-shot examples.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 33 references that are in the map. First posted on arXiv 1 Apr 2022.

Builds on

26 of 33 references.

References · 26

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  9. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  10. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  11. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  12. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 741
14 more
  1. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
  4. 2020TERA: Self-Supervised Learning of Transformer Encoder Representation for Speechcited by 186
  5. 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 170
  6. 2019SoftTriple Loss: Deep Metric Learning Without Triplet Samplingcited by 163
  7. 2019WHAM!: Extending Speech Separation to Noisy Environmentscited by 154
  8. 2020Multi-task self-supervised learning for Robust Speech Recognitioncited by 127
  9. 2021Few-Shot Keyword Spotting in Any Languagecited by 27
  10. 2021Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Losscited by 25
  11. 2020Training Keyword Spotters with Limited and Synthesized Speech Datacited by 20
  12. 2020Few-Shot Keyword Spotting With Prototypical Networkscited by 18
  13. 2021Teaching keyword spotters to spot new keywords with limited examplescited by 9
  14. 2021Representation based meta-learning for few-shot spoken intent recognitioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2023Mitigating Catastrophic Forgetting for Few-Shot Spoken Word Classification Through Meta-Learningcited by 2
  2. 2024Text-Aware Adapter for Few-Shot Keyword Spottingcited by 2
  3. 2023Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Datacited by 0
  4. 2026Scaling few-shot spoken word classification with generative meta-continual learningcited by 0