Evaluation of a Speech Recognition Prototype for Speakers with Moderate and Severe Dysarthria: A Preliminary Report
- 23 November 2010
- journal article
- research article
- Published by Taylor & Francis in Augmentative and Alternative Communication
- Vol. 26 (4) , 267-277
Abstract
This study described preliminary work with the Supplemented Speech Recognition (SSR) system for speakers with dysarthria. SSR incorporated automatic speech recognition optimized for dysarthric speech, alphabet supplementation, and word prediction. Participants included seven individuals with a range of dysarthria severity. Keystroke savings using SSR averaged 68.2% for typical sentences and 67.5% for atypical phrases. This was significantly different to using word prediction alone. The SSR correctly identified an average of 80.7% of target stimulus words for typical sentences and 82.8% for atypical phrases. Statistical significance could not be claimed for the relations between sentence intelligibility and keystroke savings or sentence intelligibility and system performance. The results suggest that individuals with dysarthria using SSR could achieve comparable keystroke savings regardless of speech severity.Keywords
This publication has 24 references indexed in Scilit:
- Speaker-independent phoneme alignment using transition-dependent statesSpeech Communication, 2009
- Speech-driven environmental control systems – a qualitative analysis of users' perceptionsDisability and Rehabilitation: Assistive Technology, 2009
- Automatic speech recognition and training for severely dysarthric users of assistive technology: The STARDUST projectClinical Linguistics & Phonetics, 2006
- Improving Intelligibility of Speakers with Profound Dysarthria and Cerebral PalsyAugmentative and Alternative Communication, 2003
- An investigation of different degrees of dysarthric speech as input to speaker-adaptive and speaker-dependent recognition systemsAugmentative and Alternative Communication, 2001
- Speech recognition training for enhancing written language generation by a traumatic brain injury survivorBrain Injury, 2000
- Model simulations of user performance with word predictionAugmentative and Alternative Communication, 1998
- Effects of speech training on the accuracy of speech recognition for an individual with a speech impairmentAugmentative and Alternative Communication, 1997
- Effect of window size on rate of communication in a lexical prediction AAC systemAugmentative and Alternative Communication, 1994
- Evaluation of keystroke savings across five assistive communication technologiesAugmentative and Alternative Communication, 1992