# GraphemeAug: A Systematic Approach to Synthesized Hard Negative Keyword Spotting Examples

arXiv: https://arxiv.org/abs/2505.14814 · HTML: https://mlsanity.com/paper/2505.14814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 18 of 18)

- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [Transformer based Grapheme-to-Phoneme Conversion](https://mlsanity.com/paper/2004.06338/) (2020)
- [End-to-End Streaming Keyword Spotting](https://mlsanity.com/paper/1812.02802/) (2018)
- [Training Keyword Spotters with Limited and Synthesized Speech Data](https://mlsanity.com/paper/2002.01322/) (2020)
- [Towards Data-efficient Modeling for Wake Word Spotting](https://mlsanity.com/paper/2010.06659/) (2020)
- [LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study](https://mlsanity.com/paper/2409.08554/) (2024)
- [Data Augmentation for Robust Keyword Spotting under Playback Interference](https://mlsanity.com/paper/1808.00563/) (2018)
- [Towards Selection of Text-to-speech Data to Augment ASR Training](https://mlsanity.com/paper/2306.00998/) (2023)
- [MM-KWS: Multi-modal Prompts for Multilingual User-defined Keyword Spotting](https://mlsanity.com/paper/2406.07310/) (2024)
- [Utilizing TTS Synthesized Data for Efficient Development of Keyword Spotting Model](https://mlsanity.com/paper/2407.18879/) (2024)
- [Small-footprint Keyword Spotting Using Deep Neural Network and Connectionist Temporal Classifier](https://mlsanity.com/paper/1709.03665/) (2017)
- [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)
- [Training Wake Word Detection with Synthesized Speech Data on Confusion Words](https://mlsanity.com/paper/2011.01460/) (2020)
- [Generating Adversarial Samples For Training Wake-up Word Detection Systems Against Confusing Words](https://mlsanity.com/paper/2201.00167/) (2022)
- [Adversarial training of Keyword Spotting to Minimize TTS Data Overfitting](https://mlsanity.com/paper/2408.10463/) (2024)
- [Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting](https://mlsanity.com/paper/2408.13355/) (2024)

## Abstract (arXiv)

Spoken Keyword Spotting (KWS) is the task of distinguishing between the presence and absence of a keyword in audio. The accuracy of a KWS model hinges on its ability to correctly classify examples close to the keyword and non-keyword boundary. These boundary examples are often scarce in training data, limiting model performance. In this paper, we propose a method to systematically generate adversarial examples close to the decision boundary by making insertion/deletion/substitution edits on the keyword's graphemes. We evaluate this technique on held-out data for a popular keyword and show that the technique improves AUC on a dataset of synthetic hard negatives by 61% while maintaining quality on positives and ambient negative audio data.