How to get the best and fairest performance out of your ASR system using activation steering

The paper explores activation steering as a method to enhance automatic speech recognition (ASR) performance and demographic fairness. It compares two techniques—paired activation subtraction and supervised optimization—finding that supervised optimization effectively improves overall ASR accuracy and fairness across gender, age, and dialect. The study also demonstrates that steering vectors trained on acoustically similar speakers can yield competitive or superior results, enabling few‑shot or zero‑shot adaptation without requiring demographic labels.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• multimodal
• safety