Scalable Keyword Spotting via Modular Network Expansion
- Published
- Source
- arXiv
- Paper number
- 697
- Field
- Research
- arXiv ID
- 2607.19918
Key points
- It freezes the entire base network, including batch-normalization statistics, so existing keyword performance is preserved at the pixel level.
- With only 10K additional parameters, 6.7% of the 150K base, it improves FRR for new keywords from 6.46% to 4.37%.
- It achieves better performance with fewer MACs, 16.34M versus 18.45M and 20.52M, than Adapter or LoRA.
- A core-first decision rule preserves the exact behavior of the existing keyword threshold.
- It can scale using only new keyword data, without access to the original training data.
Paper links
External research summaries. These are not HDATF publications or measured product results.