Ling Tze Yeoh

Date of Award

2-1-2004

Thesis Type

undergraduates

Document Type

Thesis

Divisions

fsktm

Department

Faculty of Computer Science & Information Technology

Institution

University of Malaya

Abstract

Voice recognition is the process by which a computer is able to map an acoustic signal (i.e. spoken words) to the textual representation of those words. Voice recognition is also known as Speech Recognition, Speech Understanding System or Automatic Speech Recognition (ASR). Voice recognition techniques have been in the existence for approximately 30 years and many are currently achieving an accuracy rate of approximately 99 percent for isolated word recognition. Voice recognition work now run under the gamut from practical 24 hour a day applications of isolated word recognizers in industrial or governmental operations, to research and development work in versatile recognizers of complex spoken sentences. The number of commercial devices being sold is apparently expanding exponentially, public awareness is rising and the prospects for future impact on human interaction with machines arc very bright. Voice recognition is a part of a broader speech processing technology that also involve in computer identification and verification of speakers, computer synthesis of speech and production of stored spoken responses, computer analysis of the physical and psychological state of speaker, efficient transmission of spoken conversations, detection of speech pathologist and aids to the handicapped. Isolated word recognition has many applications in the areas of voice commanded machine operation, voice dialing, command and control systems, security control and hands free cellular telephone dialing.

Note

Academic Exercise (Bachelor’s Degree) - Faculty of Computer Science & Information Technology, 2003/2004.

Download

Share

COinS