Demographics-agnostic training with augmentation and distillation reduces predictive disparity in wake-up word detection by 40-84% across demographic groups.
Following our evaluation pro- tocol, demographic groups with fewer than 20 test samples are excluded from bias quantification to ensure stable subgroup estimates
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
"OK Aura, Be Fair With Me": Demographics-Agnostic Training for Bias Mitigation in Wake-up Word Detection
Demographics-agnostic training with augmentation and distillation reduces predictive disparity in wake-up word detection by 40-84% across demographic groups.