Telemedicine or telehealth has opened a world of specialty health services to persons who may otherwise be unable to access appropriate care. Despite enormous public investment in telehealth initiatives, people who are deaf or hard of hearing encounter serious barriers in accessing current systems because of limited audio quality and limited sign language and lip reading capability. In addition, current videoconferencing systems are hardware-dependent, rendering this technology costly to initiate and upgrade. This project proposes a software driven array of adaptations to current telehealth systems that will facilitate speech and sign language comprehension. The project will achieve three aims: 1) It will enhance language comprehension by developing a real-time voice driven captioning system that automatically transcribes the speech of health care providers for display at both patient and health care provider telehealth sites, 2) It wilI facilitate lip reading and sign language reading by developing a high quality low delay software-only video coding system that can deliver clear motion scenes of lips and hands in synchrony with both speech and captions, and 3) It will evaluate the effectiveness of these technological innovations in facilitating acceptable language comprehension levels in telehealth interactions among persons across the hearing spectrum. While the proposed aims focus on persons with hearing loss, it is expected that the multimedia enhancements to telehealth will significantly benefit persons with intact hearing as well. The effects of the proposed innovations are far-reaching. Medical specialty services including: emergency services, cardiology, psychiatry, which currently use telehealth network systems will become more accessible to deaf and hard of hearing patients, including many elderly persons with hearing loss. The proposed adaptations also will allow for telehealth to support additional services such as speech/language therapy, and cognitive rehabilitation; thus, broadening the array of services available to rural and other underserved populations. Improved access to timely care for deaf and hard of hearing persons will likely improve the health of these populations. In addition, it will reduce the dual isolation of deafness in rural America. The proposed innovations will have notional and worldwide applicability and will spur health-related research in telehealth applications as well as the need of traditionally undeserved populations including deaf, hard of hearing and elderly persons.

Agency
National Institute of Health (NIH)
Institute
National Institute on Deafness and Other Communication Disorders (NIDCD)
Type
Research Project (R01)
Project #
5R01DC004340-05
Application #
6929054
Study Section
Diagnostic Imaging Study Section (DMG)
Program Officer
Cooper, Judith
Project Start
2001-08-01
Project End
2007-07-31
Budget Start
2005-08-01
Budget End
2007-07-31
Support Year
5
Fiscal Year
2005
Total Cost
$245,476
Indirect Cost
Name
University of Missouri-Columbia
Department
Biostatistics & Other Math Sci
Type
Schools of Engineering
DUNS #
153890272
City
Columbia
State
MO
Country
United States
Zip Code
65211
Zhang, Xiaojia; Zhao, Yunxin; Schopp, Laura (2007) A novel method of language modeling for automatic captioning in TC video teleconferencing. IEEE Trans Inf Technol Biomed 11:332-7