Influence of passage familiarity on intelligibility estimates of dysarthric speech

Abstract

Speech pathologists often estimate intelligibility as dysarthric speakers read standard passages. The first phase of this study compared estimates of intelligibility made by speech pathologists with transcription scores made by judges unfamiliar with the speech passages. Results indicated that speech pathologists consistently overestimated intelligibility. It was hypothesized that judge familiarity with the speech sample contributed to these inflated scores. Therefore, during the second phase of the study the influence of speech sample familiarity on estimates of intelligiblity was investigated. Group of listeners judged mild, moderate, and severely dysarthric speakers under three conditions of familiarity--Unfamiliar (passage unknown), Partially Familiar (passage read twice by a normal speaker), and Most Familiar (script of the passage available). For mild and severely dysarthric speakers, passage familiarity did not significantly influence judges' estimates. For the moderately dysarthric speaker, estimates of intelligibility increased markedly with increasing passage familiarity. Clinical implications of these results are discussed.