Bridging the Perceptual-Statistical Gap in Dysarthria Assessment: Why Machine Learning Still Falls Short

ABSTRACT Automated dysarthria detection and severity assessment from speech have attracted significant research attention due to their potential clinical impact. Despite rapid progress in acoustic modeling and deep learning, models still fall short of human expert performance. This manuscript provides a comprehensive analysis of the reasons behind this gap, emphasizing a conceptual divergence we term the "perceptual-statistical gap". We detail human expert perceptual processes, survey machine learning representations and methods, review existing literature on feature sets and modeling strategies, and present a theoretical analysis of limits imposed by label noise and inter-rater variability. We further outline practical strategies to narrow the gap, perceptually motivated features, self-supervised pre-training, ASR-informed objectives, multimodal fusion, human-in-the-loop training, and explainability methods. Finally, we propose experimental protocols and evaluation metrics aligned with clinical goals to guide future research toward clinically reliable and interpretable dysarthria assessment tools. Index T erms-- Dysarthria assessment, speech intelligibility, perceptual modeling, machine learning, human-AI gap, explainable AI, self-supervised learning 1. INTRODUCTION Dysarthria comprises a set of motor speech disorders resulting from neurological impairment such as Parkinson's disease, amyotrophic lateral sclerosis (ALS), stroke, or cerebral palsy that affect speech motor control and coordination [1].