Huntington Disease Automatic Speech Recognition with Biomarker Supervision

TL;DR

This paper explores automatic speech recognition for Huntington's disease, demonstrating how disease-specific adaptations and biomarker supervision improve recognition accuracy on a specialized clinical speech corpus.

Contribution

It introduces a novel HD-specific adaptation method, compares multiple ASR architectures, and utilizes biomarker supervision to enhance recognition performance.

Findings

HD-specific adaptation reduces WER from 6.99% to 4.95%

Parakeet-TDT outperforms other ASR architectures

Biomarker supervision reshapes error patterns in severity-dependent ways

Abstract

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.