# Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting

arXiv: https://arxiv.org/abs/2510.10740 · HTML: https://mlsanity.com/paper/2510.10740/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2025.

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

- [PTC-Bias: Phoneme-Level Temporal Competition for Bias Retrieval and Post-Decoding Correction in Speech LLMs](https://mlsanity.com/paper/2609.28727/) (2026)

## Abstract (arXiv)

In this paper, we propose DS-KWS, a two-stage framework for robust user-defined keyword spotting. It combines a CTC-based method with a streaming phoneme search module to locate candidate segments, followed by a QbyT-based method with a phoneme matcher module for verification at both the phoneme and utterance levels. To further improve performance, we introduce a dual data scaling strategy: (1) expanding the ASR corpus from 460 to 1,460 hours to strengthen the acoustic model; and (2) leveraging over 155k anchor classes to train the phoneme matcher, significantly enhancing the distinction of confusable words. Experiments on LibriPhrase show that DS-KWS significantly outperforms existing methods, achieving 6.13% EER and 97.85% AUC on the Hard subset. On Hey-Snips, it achieves zero-shot performance comparable to full-shot trained models, reaching 99.13% recall at one false alarm per hour.