Date of Award

Fall 1996

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical & Computer Engineering

Program/Concentration

Electrical Engineering

Committee Director

Stephen A. Zahorian

Committee Member

Peter L. Silsbee

Committee Member

Martin D. Meyer

Call Number for Print

Special Collections LD4331.E55C57

Abstract

A real-time visual articulation training aid has been implemented. It provides instantaneous visual feedback of vowel and stop-consonant production on a computer screen. The vowel training system corresponds to an improved floating-point implementation of a previous fixed-point system developed by Beck (1992). The new implementation provides better accuracy and an approximate five-fold increase in speed. Acoustic features computed from global short-time spectral shape are used for classification of vowels. Temporal spectral trajectories timed to begin with burst onset are used for stop consonants. A neural network is used to transform measurements of auditory stimuli from the feature space to a low-dimensionality easy-to-interpret visual representation. For stop consonant classification, errors in onset detection generate problems difficult to overcome. In this study, the Teager energy operator has been found to provide a fast and reliable way to detect stop onset. Controlled evaluation experiments were conducted on foreign speakers and hearing impaired children to determine the effect of the vowel training aid in improving vowel production. The test results seem to indicate that continuous use of the vowel training aid has a significant effect on vowel quality.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/fqvj-gy85

Download

Share

COinS