# Huntington Disease Automatic Speech Recognition with Biomarker Supervision

arXiv: https://arxiv.org/abs/2603.11168 · HTML: https://mlsanity.com/paper/2603.11168/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech](https://mlsanity.com/paper/2109.06952/) (2021)
- [Investigation of Data Augmentation Techniques for Disordered Speech Recognition](https://mlsanity.com/paper/2201.05562/) (2022)
- [EasyCall corpus: a dysarthric speech dataset](https://mlsanity.com/paper/2104.02542/) (2021)
- [The Interspeech 2025 Speech Accessibility Project Challenge](https://mlsanity.com/paper/2507.22047/) (2025)
- [Probing Whisper for Dysarthric Speech in Detection and Assessment](https://mlsanity.com/paper/2510.04219/) (2025)
- [Towards a Single ASR Model That Generalizes to Disordered Speech](https://mlsanity.com/paper/2412.19315/) (2024)
- [Classification of Manifest Huntington Disease using Vowel Distortion Measures](https://mlsanity.com/paper/2010.08503/) (2020)
- [A Self-Training Approach for Whisper to Enhance Long Dysarthric Speech Recognition](https://mlsanity.com/paper/2506.22810/) (2025)
- [Articulatory Coordination for Speech Motor Tracking in Huntington Disease](https://mlsanity.com/paper/2109.13815/) (2021)
- [Idiosyncratic Versus Normative Modeling of Atypical Speech Recognition: Dysarthric Case Studies](https://mlsanity.com/paper/2509.16718/) (2025)

## Abstract (arXiv)

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.