Dysarthria classification based on intelligibility level is useful for speech pathologists for deciding the therapy. However, intelligibility assessment also depends on perceptual attributes like hypernasality, breathiness, slow rate, short pauses etc. These perceptual attributes vary depending on the cause for dysarthria giving rise to different types of dysarthria. In this work, we explore the use of breathiness features for intelligibility assessment of dysarthria and for distinguishing type of dysarthria. Voiced segments from two controlled speakers, two dysarthric speakers with low and mid intelligibility level each from UA database are used in the work. Features were analysed for use in dysarthria intelligibility assessment vs. distinguishing type of dysarthria.
No takes yet. Share an insight, caveat, or question.
Chandrashekar et al. (2019) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: