Research Project
6787848
DESCRIPTION (provided by applicant): Commercial speech recognition software offers many people with physical limitations an important computer access method. While this access method is reasonably reliable for people with typical speech, people with motor speech disorders (dysarthria) are presently not able to reliably use this technology for writing and assistive technology control. The purpose of this research is to provide these people with a unique assistive-device access method that utilizes their speech. This will be accomplished by developing a Speech Supplemented Word Prediction Program that enables people with dysarthria to use their speech capabilities to interact with personal computers and augmentative and alternative communication software. The central element of the program will be speech-recognition software that can be trained to exploit the user's speech capabilities for use in conjunction with a custom word prediction program. The combination of the word prediction software and the speech recognition engine may provide the speaker with an effective new communication method. It may be exceptionally efficient, potentially reducing the number of keystrokes required to produce text by 75%. It also promotes the effective use of dysarthric speech for communication.
