paper 4, Word and Speaker Recognition System on MATLAB
Table of Contents
- Session 1 Software Technology and Engineering
- 1. Trust in a Hybrid Recommender System
- Session 2 Software Technology and Engineering
- 11. ReChaP Prototype: A Tool for Simplifying Requirement Change Propagation to Software Design
- 12. Risk Based Analysis for Detention Pond Overflow at Wilayah Pembangunan Iskandar (Nusajaya), Johor
- 20. A Comparative Evaluation of State-of-the-Art Approaches in the Design of an Adaptive Software System
- Session 3 Software Technology and Engineering
- 21. MiPAF: A Policy-Based Middleware Framework to Control Negative Effects of Software Evolution
- Session 4 Software Technology and Engineering
- 33. MobileObject: Fundamentals
- Session 5 Software Technology and Engineering
- 44. Abasic for Intrusion Detection System
- 48. Inhibiting Pyrolysis Process for Fiber-Reinforced Composites by Using Flame Retardants Additions
- Session 6 Computer Design and Engineering
- 55. Awareness for the Protection of Endangered Species with Augmented Reality
- Session 7 Computer Design and Engineering
- 66. Low Noise Amplifier at 5.8Ghz with Cascode and Cascaded Techniques UsingT-Matching Network for Wireless Applications
- Session 8 Computer Design and Engineering
- 75. Towards Aeroacoustic Characterization of the Sibilant [S] Production from a Simplified Parameterized Geometric Model of the Oral Cavity
- 81. Computational Algorithm to Estimate Final Costs Based on the Number of Users in Space Structures
- Session 9 Energy and Electrical Systems
- 86. Fault Diagnosis of Power Transformers with Neural Network
- 87. Influence of Particle Size and Temperature on Gasification Performance in Externally Heated Gasifier
- 90. Application of Mesh Adaptive Direct Search Method to Power System Valve-Point Economic Load Dispatch
- Session 10 Energy and Electrical Systems
- 98. Effect of Segmented Contacts on Fuel Cell Performance Using 3-D Modelling
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


This Publication
Scitation
SPIN
Scitopia
Google Scholar
PubMed