|
|
|
Project Type/Research Category: Small Business Innovation Research (SBIR), Phase I.
Funding Priority: Technology for Access and Function.
For more information on NIDRR's funding priorities, read about NIDRR's Core Areas of Research at http://www.ed.gov/rschstat/research/pubs/core-area.html.
More Accurate Voice Control Systems for the Disabled Using Improved Speech Recognition.
This project has completed its research activities and is now closed. Check REHABDATA for documents.
Amazability, Inc..
14 Lorraine Circle.
Waban, MA 02468-1466.
E-mail: amazability@rcn.com.
Principal Investigator: Kenneth R. Ingham, PhD.
Public Contact Phone: 617/795-0134.
Project Number: H133S020107 (See also H133S030005).
Start Date: October 1, 2002.
Length: 6 months.
NIDRR Officer: Carol Cohen.
NIDRR Funding: FY 02 $74,200.
Abstract:
This project designs and tests interface software that, in combination with an innovative speech recognition system, can improve current recognition maxima for non-spontaneous utterances from approximately 85 percent to approaching 100 percent. The project tests statistical and grammar-driven recognition models in a series of bench trials designed to quantify accuracy, speed of use, and overall productivity as compared to existing adaptive technology. Bringing accuracy as close as possible to 100 percent should allow the software to overcome a major obstacle in the use of speech recognition by people who are blind or who have other disabilities: the tendency to become lost and unable to complete computer-assisted tasks. A secondary goal is research into the development of a closely coupled series of resets integrated with applications designed from the ground up for speech input/output, intended to support command and control and to eliminate the "getting lost" problem.
Descriptors: Speech recognition, Computer applications, Visual impairments.
Documents in REHABDATA:
There are no documents related to this project.
|
|
