alexa The design of CAST (Computer-Aided Speechreading Training).


Journal of Communication Disorders, Deaf Studies & Hearing Aids

Author(s): PichoraFuller MK, Benguerel AP

Abstract Share this page

Abstract The underlying theoretical assumptions, goals, design, and implementation of a Computer-Aided Speechreading Training system (CAST) are described as a case study in program design. This computerized speechreading assessment and training system simulates face-to-face intervention and is designed to be one component of a comprehensive aural rehabilitation program for preretirement adults with acquired mild-to-moderate hearing loss. The interactive, automated course consists of eight training lessons, each focusing on a particular viseme that is practiced by a modified discourse tracking method using viseme-specific texts. Three basic speechreading skills are emphasized: visual speech perception, use of linguistic redundancy, and use of feedback between message sender and receiver. These skills are evaluated separately by means of CAST tracking rate, receiver strategy, and inferred error type. Four example case assessments are provided to illustrate the potential applications of CAST as a standardizable rehabilitative tool. An independent program evaluation is provided in a companion paper (Gagné, Dinon, & Parsons, 1991). Comparisons between CAST, face-to-face tracking procedures, and natural discourse are presented and discussed with reference to theoretical and clinical issues in speechreading and program evaluation.
This article was published in J Speech Hear Res and referenced in Journal of Communication Disorders, Deaf Studies & Hearing Aids

Relevant Expert PPTs

Relevant Speaker PPTs

Recommended Conferences

Peer Reviewed Journals
Make the best use of Scientific Research and information from our 700 + peer reviewed, Open Access Journals
International Conferences 2017-18
Meet Inspiring Speakers and Experts at our 3000+ Global Annual Meetings

Contact Us

© 2008-2017 OMICS International - Open Access Publisher. Best viewed in Mozilla Firefox | Google Chrome | Above IE 7.0 version