Lee, I. X. C. (2011). The application of speech recognition technology for remediating the writing difficulties of students with learning disabilities (Publication No. 3501541) [Doctoral dissertation, University of Washington]. ProQuest Dissertations and Theses Global. https://www.proquest.com/docview/937166217

University of Washington (Seattle, WA); ProQuest document ID: 937166217

The use of speech recognition technology for writing by students with learning disabilities was examined. Two speech-to-text conditions were examined. Speech recognition software (SR) allowed students to monitor what they said and edit the text as they spoke. Simplified dictation mode using a digital voice recorder (DR) did not provide students with immediate visual text or allow them to edit text as they spoke.

Four 9-year-old students with learning disabilities and with goals related to writing in their Individualized Education Plan (IEP) were included in this study. Students were from elementary schools in the Seattle Public School District.

Fluency and quality of writing were examined across three conditions to assess students’ writing. Total text produced or text length, text production rate (wpm), and total number of T-units were used to measure writing fluency. Percentage of surface errors, T-unit length, clause length, and clauses per T-unit were used to measure text complexity. Story structure level was used to measure general writing quality or language organization. In all three conditions, students completed narrative writing tasks taken from a criterion referenced assessment and treatment program called The Expression Connection (Klecan-Aker & Brueggeman, 1991). One writing condition required students to complete the task using traditional paper-pencil. The second and third conditions required students to complete the task using variations of speech-to-text technology (speech recognition software and simplified dictation mode using a digital voice recorder (DR)).

The two speech-to-text conditions (SR and DR) produced better writing outcomes for all participants compared to the traditional paper-pencil condition. Individual student needs and abilities influenced which speech-to-text condition (SR or DR) was most effective for a student.