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

arXiv: https://arxiv.org/abs/2506.17686 · HTML: https://mlsanity.com/paper/2506.17686/

## Key facts

- Cited by 1 papers 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 (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace](https://mlsanity.com/paper/1910.04855/) (2019)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Few-Shot Keyword Spotting in Any Language](https://mlsanity.com/paper/2104.01454/) (2021)
- [Learning Efficient Representations for Keyword Spotting with Triplet Loss](https://mlsanity.com/paper/2101.04792/) (2021)
- [How Should We Extract Discrete Audio Tokens from Self-Supervised Models?](https://mlsanity.com/paper/2406.10735/) (2024)
- [Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models](https://mlsanity.com/paper/2210.16043/) (2022)
- [Few-Shot Keyword Spotting With Prototypical Networks](https://mlsanity.com/paper/2007.14463/) (2020)
- [Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems](https://mlsanity.com/paper/2306.02161/) (2023)
- [Dummy Prototypical Networks for Few-Shot Open-Set Keyword Spotting](https://mlsanity.com/paper/2206.13691/) (2022)
- [Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors](https://mlsanity.com/paper/2408.12481/) (2024)
- [Fully Unsupervised Training of Few-shot Keyword Spotting](https://mlsanity.com/paper/2210.02732/) (2022)

## Built on by (most cited first, 1 of 1)

- [EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spotting](https://mlsanity.com/paper/2601.16316/) (2026)

## 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.