Dictation and Speech Recognition Technology as Test Accommodations

Abstract

This study addressed the feasibility and validity of dictation using speech recognition software and dictation to a scribe as accommodations for tests involving extended writing. On the issue of feasibility, high school students with and without learning disabilities (LD) learned to use speech recognition software with acceptable accuracy. Total word errors with speech recognition were under 10%, and there were few unreadable words. On the issue of writing quality, for students with LD, essays dictated using speech recognition were better than handwritten essays, and essays dictated to a scribe were even better. No differences in quality were found for students without LD. The results provide support for the validity of dictation as a test accommodation.