PROJECT SUMMARY Dysarthria is a motor speech impairment characterized by sensorimotor abnormalities that affect the movements required for speech, frequently resulting in reduced speech intelligibility and naturalness [1], [2]. Dysarthria often significantly impairs communication, in turn threatening a patient’s participation in daily life activities and quality of life [2]–[7]. However, relatively few treatments for dysarthria exist, and patient access to treatments is often limited by financial and geographic barriers [8]–[10]. Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease characterized by the progressive loss of upper and lower motor neurons. Nearly all individuals with ALS will at some point experience speech impairment [11], [12], characterized by flaccid, spastic, or mixed flaccid- spastic dysarthria. Given the devastating loss of speech in ALS, there is a critical need for evidence-based treatments to help patients maintain their functional speech. Clear speech, which trains a mode of speech with deliberate enunciation, is a successful dysarthria treatment that globally affects the speech system and intelligibility. However, clear speech training uses subjective feedback from a partner, and its effects on intelligibility in ALS have been understudied. Additionally, although increased practice amount has been associated with positive motor learning outcomes in people with unimpaired motor function [13], [69], there is a dearth of research into the effects of single-session practice dosage on impaired limb [57] and motor speech function [10], [14]. This study investigates a novel method for providing feedback using noise-augmented automatic speech recognition to automatically and objectively facilitate clear speech treatment in healthy participants and participants with bulbar ALS. It also examines the effects of single-session practice dosage on learning a clear mode of speaking. Preliminary results support both nASR and increased practice dosage for facilitating clear speech.