One-shot, one-epoch fine-tuning of only the last layer of a pretrained keyword spotter yields reported accuracy gains of 4.9% to 46.0% under car horn, dog bark, and street music noise.
Automatic gain control and multi-style training for robust small- footprint keyword spotting with deep neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adaptive Noise Resilient Keyword Spotting Using One-Shot Learning
One-shot, one-epoch fine-tuning of only the last layer of a pretrained keyword spotter yields reported accuracy gains of 4.9% to 46.0% under car horn, dog bark, and street music noise.