# Training Keyword Spotters with Limited and Synthesized Speech Data

arXiv: https://arxiv.org/abs/2002.01322 · HTML: https://mlsanity.com/paper/2002.01322/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jan 2020.

## Built on by (most cited first, 20 of 20)

- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Keyword Transformer: A Self-Attention Model for Keyword Spotting](https://mlsanity.com/paper/2104.00769/) (2021)
- [Broadcasted Residual Learning for Efficient Keyword Spotting](https://mlsanity.com/paper/2106.04140/) (2021)
- [Deep Spoken Keyword Spotting: An Overview](https://mlsanity.com/paper/2111.10592/) (2021)
- [Few-Shot Keyword Spotting in Any Language](https://mlsanity.com/paper/2104.01454/) (2021)
- [Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition](https://mlsanity.com/paper/2110.11479/) (2021)
- [Teaching keyword spotters to spot new keywords with limited examples](https://mlsanity.com/paper/2106.02443/) (2021)
- [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)
- [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)
- [Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model](https://mlsanity.com/paper/2407.18879/) (2024)
- [Neural Model Reprogramming with Similarity Based Mapping for Low-Resource Spoken Command Recognition](https://mlsanity.com/paper/2110.03894/) (2021)
- [Synth4Kws: Synthesized Speech for User Defined Keyword Spotting in Low Resource Environments](https://mlsanity.com/paper/2407.16840/) (2024)
- [GE2E-KWS: Generalized End-to-End Training and Evaluation for Zero-shot Keyword Spotting](https://mlsanity.com/paper/2410.16647/) (2024)
- [Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting](https://mlsanity.com/paper/2408.10463/) (2024)
- [AraSpot: Arabic Spoken Command Spotting](https://mlsanity.com/paper/2303.16621/) (2023)
- [Plug-and-Play Multilingual Few-shot Spoken Words Recognition](https://mlsanity.com/paper/2305.03058/) (2023)
- [Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR](https://mlsanity.com/paper/2403.10937/) (2024)
- [Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space](https://mlsanity.com/paper/2409.12745/) (2024)
- [GraphemeAug: A Systematic Approach to Synthesized Hard Negative Keyword Spotting Examples](https://mlsanity.com/paper/2505.14814/) (2025)

## Abstract (arXiv)

With the rise of low power speech-enabled devices, there is a growing demand to quickly produce models for recognizing arbitrary sets of keywords. As with many machine learning tasks, one of the most challenging parts in the model creation process is obtaining a sufficient amount of training data. In this paper, we explore the effectiveness of synthesized speech data in training small, spoken term detection models of around 400k parameters. Instead of training such models directly on the audio or low level features such as MFCCs, we use a pre-trained speech embedding model trained to extract useful features for keyword spotting models. Using this speech embedding, we show that a model which detects 10 keywords when trained on only synthetic speech is equivalent to a model trained on over 500 real examples. We also show that a model without our speech embeddings would need to be trained on over 4000 real examples to reach the same accuracy.