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.
Abstract (translated)
自动语音识别（ASR）在处理病理性的言语，尤其是亨廷顿病（HD）患者的言语时，仍然是一项未被充分研究的领域。亨廷顿病患者常表现出不规则的时间感、不稳定的声音产生和发音扭曲等问题，这对现有的模型构成了挑战。 我们提出了一项系统性针对亨廷顿病ASR的研究，使用了一个此前从未用于端到端ASR训练的高保真临床语音语料库。我们在统一评估框架下对比了多个ASR家族，并分析了WER（单词错误率）、替换、删除和插入模式等指标。 研究发现，亨廷顿病患者的言语会导致特定架构下的错误模式，其中Parakeet-TDT模型在性能上超过了编码器-解码器及CTC基准模型。针对亨廷顿病的特异性适应性调整将WER从6.99%降低到4.95%，我们还提出了一种基于生物标志物辅助监督的方法，并分析了如何以依赖疾病严重程度的方式重塑错误行为，而不是单纯地提高WER。 我们的研究代码和模型现已开源。
URL
https://arxiv.org/abs/2603.11168
