Self-supervised speech encoders show speaker-group bias from the first latent layers, with SID bias lowest where overall error is lowest while ASR bias is highest where overall error is lowest; the ASR pattern persists after fine-tuning.
Vers l’apprentissage de mod `eles auto-supervis ´es de reconnais- sance automatique de la parole plus ´equitables sans a priori d´emographique
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
-
Where Do Self-Supervised Speech Models Become Unfair?
Self-supervised speech encoders show speaker-group bias from the first latent layers, with SID bias lowest where overall error is lowest while ASR bias is highest where overall error is lowest; the ASR pattern persists after fine-tuning.