Huntington Disease Automatic Speech Recognition with Biomarker Supervision
This addresses the problem of pathological speech recognition for Huntington's disease patients, representing an incremental advance in a niche domain.
The study tackled automatic speech recognition for Huntington's disease speech, achieving a reduction in word error rate from 6.99% to 4.95% through HD-specific adaptation and analyzing error patterns.
Automatic speech recognition (ASR) for pathological speech remains underexplored, especially for Huntington's disease (HD), where irregular timing, unstable phonation, and articulatory distortion challenge current models. We present a systematic HD-ASR study using a high-fidelity clinical speech corpus not previously used for end-to-end ASR training. We compare multiple ASR families under a unified evaluation, analyzing WER as well as substitution, deletion, and insertion patterns. HD speech induces architecture-specific error regimes, with Parakeet-TDT outperforming encoder-decoder and CTC baselines. HD-specific adaptation reduces WER from 6.99% to 4.95% and we also propose a method for using biomarker-based auxiliary supervision and analyze how error behavior is reshaped in severity-dependent ways rather than uniformly improving WER. We open-source all code and models.