Psychoacoustic Framework for Automated Dysarthria Severity Assessment Via Hybrid Acoustic Ensembles

Dysarthria is a neurological motor speech disorder that affects speech production and intelligibility through impairments in articulation, phonation, and prosody.Reliable severity assessment is important for clinical diagnosis and long-term monitoring, yet existing automated systems rely heavily on Mel-Frequency Cepstral Coefficients (MFCCs), which may not adequately capture subtle pathological speech variations.This work investigates