Award Date

1-1-1998

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Committee Member

Evangelos A. Yfantis

Number of Pages

128

Abstract

The art and science of speech recognition have been advanced to the state where it is now possible to communicate reliably with a computer by speaking to it in a disciplined manner using a vocabulary of moderate size. There are many applications of speech recognition technology in telecommunications and other fields. Voice Interactive Computer Graphics And Games (VICGG) describes and emphasizes how voice recognition can be applied to design a real-time interactive graphics system. The VICGG system consists of a recognition module and a graphics module; The recognition module is used for isolated word recognition. Three separate implementations of recognition algorithms have been evaluated. The first algorithm illustrate the effect of noise reduction filters in the recognition process. The second algorithm usee a noise-gate in the recognition process. The third algorithm is an improved version of the first two and is implemented using short-time Fourier analysis and bank of filters. The relative merits and demerits of these algorithm have been discussed. Using a vocabulary of moderate size, accuracy and real-time performance have been achieved in the third algorithm; The graphics module has a set of 3-dimensional Dinosaur animations, which are totally controlled by the recognition module. The event driven graphics module is implemented using OpenGL. The recognized word from the recognition module is linked to a corresponding animation in the graphics module; The VICGG sysem demonstrates how speech technology will play an increasingly important role in the current multimedia era. This reaserch also illustrates the applications of speech recogntion technology in diverse fields.

Keywords

Computer; Games; Graphics; Interaction; Voice

Controlled Subject

Computer science

Disciplines

Higher Education

File Format

pdf

File Size

1.98 MB

Degree Grantor

University of Nevada, Las Vegas

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Identifier

English


Share

COinS