# Few-Shot Keyword Spotting in Any Language

arXiv: https://arxiv.org/abs/2104.01454 · HTML: https://mlsanity.com/paper/2104.01454/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 3 Apr 2021.

## Builds on (most cited first, 13 of 13)

- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems](https://mlsanity.com/paper/2010.08678/) (2020)
- [Hello Edge: Keyword Spotting on Microcontrollers](https://mlsanity.com/paper/1711.07128/) (2017)
- [Deep Residual Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/1710.10361/) (2017)
- [Query-by-Example Keyword Spotting system using Multi-head Attention and Softtriple Loss](https://mlsanity.com/paper/2102.07061/) (2021)
- [Training Keyword Spotters with Limited and Synthesized Speech Data](https://mlsanity.com/paper/2002.01322/) (2020)
- [Predicting detection filters for small footprint open-vocabulary keyword spotting](https://mlsanity.com/paper/1912.07575/) (2019)
- [Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoring](https://mlsanity.com/paper/1806.09374/) (2018)
- [Multilingual bottleneck features for subword modeling in zero-resource languages](https://mlsanity.com/paper/1803.08863/) (2018)

## Built on by (most cited first, 27 of 27)

- [DataPerf: Benchmarks for Data-Centric AI Development](https://mlsanity.com/paper/2207.10062/) (2022)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language](https://mlsanity.com/paper/2311.08323/) (2023)
- [Few-Shot Open-Set Learning for On-Device Customization of KeyWord Spotting Systems](https://mlsanity.com/paper/2306.02161/) (2023)
- [Progressive Continual Learning for Spoken Keyword Spotting](https://mlsanity.com/paper/2201.12546/) (2022)
- [Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting](https://mlsanity.com/paper/2203.16361/) (2022)
- [Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors](https://mlsanity.com/paper/2408.12481/) (2024)
- [What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice](https://mlsanity.com/paper/2105.04674/) (2021)
- [On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting](https://mlsanity.com/paper/2204.00352/) (2022)
- [From Tiny Machine Learning to Tiny Deep Learning: A Survey](https://mlsanity.com/paper/2506.18927/) (2025)
- [AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spotting](https://mlsanity.com/paper/2505.11817/) (2025)
- [Locale Encoding For Scalable Multilingual Keyword Spotting Models](https://mlsanity.com/paper/2302.12961/) (2023)
- [Latent Phrase Matching for Dysarthric Speech](https://mlsanity.com/paper/2306.05446/) (2023)
- [Text-Aware Adapter for Few-Shot Keyword Spotting](https://mlsanity.com/paper/2412.18142/) (2024)
- [Exploring Representation Learning for Small-Footprint Keyword Spotting](https://mlsanity.com/paper/2303.10912/) (2023)
- [Efficiently Identifying Low-Quality Language Subsets in Multilingual Datasets: A Case Study on a Large-Scale Multilingual Audio Dataset](https://mlsanity.com/paper/2410.04292/) (2024)
- [Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models](https://mlsanity.com/paper/2506.17686/) (2025)
- [Nonverbal Sound Detection for Disordered Speech](https://mlsanity.com/paper/2202.07750/) (2022)
- [Plug-and-Play Multilingual Few-shot Spoken Words Recognition](https://mlsanity.com/paper/2305.03058/) (2023)
- [SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting](https://mlsanity.com/paper/2409.09067/) (2024)
- [Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detection](https://mlsanity.com/paper/2501.11631/) (2025)
- [A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains](https://mlsanity.com/paper/2504.04017/) (2025)
- [PatchDSU: Uncertainty Modeling for Out of Distribution Generalization in Keyword Spotting](https://mlsanity.com/paper/2508.03190/) (2025)
- [Zero-Shot KWS for Children's Speech using Layer-Wise Features from SSL Models](https://mlsanity.com/paper/2508.21248/) (2025)
- [EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spotting](https://mlsanity.com/paper/2601.16316/) (2026)
- [Does language matter for spoken word classification? A multilingual generative meta-learning approach](https://mlsanity.com/paper/2605.13084/) (2026)
- [Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning](https://mlsanity.com/paper/2607.29353/) (2026)

## Abstract (arXiv)

We introduce a few-shot transfer learning method for keyword spotting in any language. Leveraging open speech corpora in nine languages, we automate the extraction of a large multilingual keyword bank and use it to train an embedding model. With just five training examples, we fine-tune the embedding model for keyword spotting and achieve an average F1 score of 0.75 on keyword classification for 180 new keywords unseen by the embedding model in these nine languages. This embedding model also generalizes to new languages. We achieve an average F1 score of 0.65 on 5-shot models for 260 keywords sampled across 13 new languages unseen by the embedding model. We investigate streaming accuracy for our 5-shot models in two contexts: keyword spotting and keyword search. Across 440 keywords in 22 languages, we achieve an average streaming keyword spotting accuracy of 87.4% with a false acceptance rate of 4.3%, and observe promising initial results on keyword search.