Automatic estimation of verbal fluency index in people with Motor Neuron Disease using ASR alignment and pause modelling

利用 ASR 对齐与停顿建模自动评估运动神经元病患者的言语流畅度指数

Monitoring cognitive impairment (CI) in motor neuron disease (MND) is essential for timely treatment and care, yet challenging due to co-occurring speech difficulties. The Edinburgh Cognitive and Behavioural ALS Screen (ECAS) provides a robust metric for CI assessment, with the Verbal Fluency Index (VFI) a central element. 监测运动神经元病（MND）患者的认知障碍（CI）对于及时治疗和护理至关重要，但由于患者常伴有言语障碍，这一过程极具挑战性。“爱丁堡认知与行为肌萎缩侧索硬化症筛查”（ECAS）为评估认知障碍提供了一套可靠的指标，其中言语流畅度指数（VFI）是核心要素。

Building on recent advances in automated speech analysis, this study proposes a system for estimating VFI. It leverages a unique MND dataset and combines ASR (WhisperX) and VAD (Silero) with refined timestamping to predict the VFI and extract several clinically interpretable measures. 基于自动语音分析领域的最新进展，本研究提出了一种用于评估 VFI 的系统。该系统利用了一个独特的 MND 数据集，结合了自动语音识别（WhisperX）和语音活动检测（Silero）技术，并通过精确的时间戳对齐来预测 VFI，同时提取出多项具有临床解释意义的指标。

Our approach outperformed systems based on traditional acoustic features and self-supervised embeddings, evaluated using multiple regression algorithms. Clinically inspired features consistently outperformed the other sets, with the best models achieving strong results (P-words: R2 0.9, NRMSE 0.05; S-words: R2 0.8, NRMSE 0.08), demonstrating the feasibility of automated VFI estimation. 通过多种回归算法评估，我们的方法在性能上优于基于传统声学特征和自监督嵌入（embeddings）的系统。临床启发式特征在所有测试中表现最为稳定，最优模型取得了显著成果（P 类词：R2 0.9，NRMSE 0.05；S 类词：R2 0.8，NRMSE 0.08），证明了自动评估 VFI 的可行性。