mlsanityData to 14 Oct 2026

Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models

arXiv 2506.17686 ↗First posted 21 Jun 2025eess.AS cs.CL cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

Keyword Spotting plays a critical role in enabling hands-free interaction for battery-powered edge devices. Few-Shot Keyword Spotting (FS-KWS) addresses the scalability and adaptability challenges of traditional systems by enabling recognition of custom keywords with only a few examples. However, existing FS-KWS systems achieve subpar accuracy at desirable false acceptance rates, particularly in resource-constrained edge environments. To address these issues, we propose a training scheme that leverages self-supervised learning models for robust feature extraction, dimensionality reduction, and knowledge distillation. The teacher model, based on Wav2Vec 2.0 is trained using Sub-center ArcFace loss, which enhances inter-class separability and intra-class compactness. To enable efficient deployment on edge devices, we introduce attention-based dimensionality reduction and train a standard lightweight ResNet15 student model. We evaluate the proposed approach on the English portion of the Multilingual Spoken Words Corpus (MSWC) and the Google Speech Commands (GSC) datasets. Notably, the proposed training method improves the 10-shot classification accuracy from 33.4% to 74.1% on 11 classes at 1% false alarm accuracy on the GSC dataset, thus making it significantly better-suited for a real use case scenario.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 18 of its 26 references that are in the map. First posted on arXiv 21 Jun 2025.

Builds on

18 of 26 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  7. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  8. 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
  9. 2017Deep Residual Learning for Small-Footprint Keyword Spottingcited by 68
  10. 2021Few-Shot Keyword Spotting in Any Languagecited by 27
  11. 2021Learning Efficient Representations for Keyword Spotting with Triplet Losscited by 24
  12. 2024How Should We Extract Discrete Audio Tokens from Self-Supervised Models?cited by 24
6 more
  1. 2022Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Modelscited by 21
  2. 2020Few-Shot Keyword Spotting With Prototypical Networkscited by 18
  3. 2023Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systemscited by 9
  4. 2022Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spottingcited by 7
  5. 2024Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensorscited by 7
  6. 2022Fully Unsupervised Training of Few-shot Keyword Spottingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spottingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023On-Device Constrained Self-Supervised Speech Representation Learning for Keyword Spotting via Knowledge Distillation
  2. 2024GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting
  3. 2022Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge Microcontrollers
  4. 2022Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
  5. 2023VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks
  6. 2025Keyword Mamba: Spoken Keyword Spotting with State Space Models
  7. 2022Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting
  8. 2026Domain-Incremental Continual Learning for Robust and Efficient Keyword Spotting in Resource Constrained Systems