mlsanityData to 14 Oct 2026

Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting

arXiv 2206.13691 ↗First posted 28 Jun 2022cs.SD cs.LG eess.AScited by 7

Not on the map. Why?

Abstract (arXiv)

Keyword spotting is the task of detecting a keyword in streaming audio. Conventional keyword spotting targets predefined keywords classification, but there is growing attention in few-shot (query-by-example) keyword spotting, e.g., N-way classification given M-shot support samples. Moreover, in real-world scenarios, there can be utterances from unexpected categories (open-set) which need to be rejected rather than classified as one of the N classes. Combining the two needs, we tackle few-shot open-set keyword spotting with a new benchmark setting, named splitGSC. We propose episode-known dummy prototypes based on metric learning to detect an open-set better and introduce a simple and powerful approach, Dummy Prototypical Networks (D-ProtoNets). Our D-ProtoNets shows clear margins compared to recent few-shot open-set recognition (FSOSR) approaches in the suggested splitGSC. We also verify our method on a standard benchmark, miniImageNet, and D-ProtoNets shows the state-of-the-art open-set detection rate in FSOSR.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 30 of its 40 references that are in the map. First posted on arXiv 28 Jun 2022.

Builds on

30 of 40 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2016Layer Normalizationcited by 5,669
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  8. 2016Matching Networks for One Shot Learningcited by 2,255
  9. 2017Deep Setscited by 1,421
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  11. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  12. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
18 more
  1. 2015Towards Open Set Deep Networkscited by 538
  2. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  3. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  4. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  5. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  6. 2018Classification-Reconstruction Learning for Open-Set Recognitioncited by 146
  7. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  8. 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
  9. 2020Few-Shot Open-Set Recognition using Meta-Learningcited by 50
  10. 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 48
  11. 2021Few-shot Open-set Recognition by Transformation Consistencycited by 29
  12. 2021Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Losscited by 25
  13. 2019Query-by-example on-device keyword spottingcited by 19
  14. 2020Few-Shot Keyword Spotting With Prototypical Networkscited by 18
  15. 2022Domain Generalization with Relaxed Instance Frequency-wise Normalization for Multi-device Acoustic Scene Classificationcited by 16
  16. 2020Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-footprint Keyword Spottingcited by 15
  17. 2019Orthogonality Constrained Multi-Head Attention For Keyword Spottingcited by 6
  18. 2021Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalizationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  2. 2023Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systemscited by 9
  3. 2024Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensorscited by 7
  4. 2026Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypescited by 2
  5. 2025Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Modelscited by 1
  6. 2023Improving Small Footprint Few-shot Keyword Spotting with Supervision on Auxiliary Datacited by 0
  7. 2024Unlocking Transfer Learning for Open-World Few-Shot Recognitioncited by 0