Text Increase Text Decrease Text Reset

paper 4, Word and Speaker Recognition System on MATLAB

In Session 1 Software Technology and Engineering from: International Conference on Software Technology and Engineering, 3rd (ICSTE 2011)
Author(s)/Editor(s): Mohamed Othman, Raja Suzana Raja Kasim
859797 Cover Image
Published: 2011
Author(s)/Editor(s): Tan Shwu Fei, Mohammad Awan
Chapter Page Count: 5 pages

Table of Contents

  • Preview

Chapter Contents

  • Abstract
  • Key Words
  • 1. Introduction
  • 2. Background Study
  • 3. Problem Statement
  • 4. Objectives & Scope of Study
  • 5. Methodology
  • 6. Result and Discussion
  • 8. Conclusion & Recommendation
  • References

Excerpt

A system which combines user dependent Word Recognition and text dependent speaker recognition is described. Word recognition is the process of converting an audio signal, captured by a microphone, to a word. Voice Activity Detection (VAD), Spectral Subtraction (SS), Mel-Frequency Cepstrum Coefficient (MFCC), Vector Quantization (VQ), Dynamic Time Warping (DTW) and k-Nearest Neighbour (k-NN) are methods used in word recognition part of the project to implement using MATLAB software. For Speaker Recognition part, Vector Quantization (VQ) is used. The recognition rate for word and speaker recognition system that was successfully implemented is 87.04% for word recognition while for speaker recognition is 64.81%.



©2011 ASME


close