SOURCE-LINKED INTELLIGENCE

A Probe Shift Is Not a Fairness Fix: The Limits of Representation Steering in Speech Models

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Automatic speech recognition (ASR) systems exhibit unequal error rates across speaker groups, motivating interventions on their internal representations. We ask whether speaker-linked attributes that are linearly readable from pretrained ASR encoders yield useful directions for reducing group word-error-rate (WER) gaps. Across Whisper-medium, HuBERT-large, and Wav2Vec2-large on Common Voice and the Speech Accent Archive, we probe every encoder layer for metadata-derived sex/gender, age, and native/accent labels; construct centroid and probe-derived directions; inject them at selected layers; a

Read original source ↗ Open in workspace

recordType

paper

region

Global