Real Time Speech Recognition System

Nor Rifhan , Zahari (2009) Real Time Speech Recognition System. Project Report. UTeM, Melaka,Malaysia. (Submitted)

	PDF (24 Pages) Real_Time_Speech_Recognition_System_Nor_Rifhan_Binti_Zahari_TK7882.S65.N74_2009_-_24_Pages.pdf - Submitted Version Download (4MB)
	PDF (Full Text) Real_Time_Speech_Recognition_System_Nor_Rifhan_Binti_Zahari_TK7882.S65.N74_2009.pdf - Submitted Version Restricted to Registered users only Download (16MB)

Abstract

The purpose of this project is to develop a real time speech recognition system. The function of this speech recognition system is to the system unlock upon recognizing a voice password spoken by administrator or password holder. This project highlights the development of speech recognition using Matlab 7.0 to recognize the input speech. This system can be used as a security system such as Verification for Assessing Entry Application and Password Substitutions. The main objective of this project is to design the voice recognition system. Analysis of the voice is made using correlation and the regression method to compare the voiceprint of different words. These techniques provide stronger ability to recognize the same word. Voice training session is very important for the system to identify accurate frequency spectrum for one word. The training procedure is also used to reduce the random changes due to one word is spoken different times. The experimental results demonstrate high accuracy for this real time voice recognition system.

Actions (login required)

View Item