Project 3 - CORE Project for Computer Enabled and Distance Aural Rehabilitation
H. Timothy Bunnell, Ph.D. - Wilmington, DE / A. I. duPont Hospital for Children
Purpose of Study
The purpose of this ‘core’ project is to provide text-to-speech synthesis and Automatic Speech Recognition (ASR) tools for other projects within the RERC-HE. The project focuses on issues surrounding (a) the design of concatenative TTS voices for aural rehabilitation, and (b) the development of ASR technology for utterance verification. Both of these areas will build upon the ModelTalker TTS system, software developed in the Speech Research Laboratory at the Alfred I. duPont Hospital for Children as part of an on-going project to develop personalized synthetic voices for augmented communicators.
This project involves the development of new tools based on the ModelTalker TTS system and affiliated speech recording software that will allow us to create synthetic voices designed for optimal use in Aural Rehabilitation (AR) applications. We will systematically explore how TTS quality affects the perception of synthetic speech by aided hearing impaired listeners and what level of TTS quality is necessary to support AR applications. In addition to the generation of synthetic voices for various projects, this core will be involved in porting utterance verification technology presently implemented in the ModelTalker speech recording software to a variety of AR applications.
H. Timothy Bunnell
Email - email@example.com
Phone - (302) 651-6835