Human-calibrated automated intelligibility evaluation of speech neuroprostheses
Aparna Srinivasan, Maitreyee Wairagkar, Ramie Wakeb, Dana Farias, Lee M. Miller, David M. Brandman, Sergey D. Stavisky
This paper fine-tunes an ASR model on human-transcribed synthesized speech to better align its word error rate with human perception, achieving higher correlation than zero-shot ASR.
bioRxiv · Oct 28, 2026 · PreprintNeuroscience