“In Pursuit of Global Competitiveness”
Project Report On
SPEAKER RECOGNITION USING VECTOR QUANTIZATION
Submitted By
SARATH KOLLI (T.E. E&TC) MAYUR BHAMRE (T.E. E&TC) SHRIKANT MALI (T.E. E&TC)
Exam. No. Exam. No. Exam. No.
Department of Electronics & Telecommunication Engineering MET’S Institute of Engineering,BKC,Nashik.
(2008 - 2009)
CERTIFICATE This is to certify that, the project “Speaker Recognition Using Vector Quantization” submitted by Sarath Kolli, is a bonafide work completed under the supervision and guidance in partial fulfilment for Electronics System Design Lab. Mini Project (T.E. E&TC) at MET’S Institute of Engineering, BKC, affiliated to University of Pune (M.S.).
Place: Nashik
Date:
Prof. Risodkar Y.R. / Prof. Nandre A.G. Project Coordinator Department of Electronics & Telecommunication Engineering.
Prof. Patil D.P. Head Department of Electronics & Telecommunication Engineering.
Principal MET’S Institute of Engineering, BKC, Nashik (M.S.) – 422003
List of Abbreviations List of Figures List of Graphs List of Tables
1. INTRODUCTION 1.1 1.2 1.3 1.4 1.5
Introduction Necessity Objectives Theme Organization
2. LITERATURE SURVEY 2.1 Historical Background
3.3.3 Computing Weights 3.4 Decision
4. PERFORMANCE ANALYSIS 4.1 4.2 4.3 4.4
MFCC Analysis Experimental analysis Training and Testing Results
47 48
49 49 52 61 63
5. CONCLUSIONS
75
5.1 Conclusions 5.2 Future Scope 5.3 Applications
75 75 76
Appendices Cost Estimation References Acknowledgment
77 78 80 81
List of Abbreviations Symbol PIN FAR FMR EER NIST STFT FFT IDFT MFCC DCT LPC LPCC DTW VQ MSE GLA TT GMM HMM
Illustrations Personal Identification Number False Acceptance Rate False Rejection Rate Equal Error Rate National Institute of Standard and Technology Short Term Fourier Transform Fast Fourier Transform Inverse Discrete Fourier Transform Mel Frequency Cepstrum Coefficients Discrete Cosine Transform Linear Predictive Coding Linear Predictive Cepstral Coefficients Dynamic Time Warping Vector Quantization Mean Squared Error Generalized Lloyd Algorithm Texas Instruments Gaussian Mixture Modeling Hidden Markov Modeling
Figure
Illustrations
2.1
Speaker Recognition
2.2
Speaker verification s
2.3
Speaker Identification
2.4
Human Voice Produc
2.5
Global Airflow and S
2.6
Wideband and Narro
2.7
Vocal Tract Model
2.8
Source Filter Model
Graph
Illustrations
4.1
Identification Rate fo
4.2
Identification Rate fo
4.3
Identification Rate fo
4.4
Identification Rate fo
4.5
Identification Rate fo
4.6
Identification Rate fo
4.7
Identification Rate fo
4.8
Identification Rate fo
Table
Illustrations
2.1
Historical Review of S
4.1
Numerical Examples Algorithm
4.2
Performance Measure
4.3
Comparison of Succe Duration.
4.4
Comparison of Succe Duration.
4.5
Comparison of Succe
Acknowledgment I take this opportunity to express my heart-felt gratitude to Project Coordinators for their constant encouragement, able guidance and support throughout the course of this semester. I sincerely thank Prof. Rehpade R.B. Principal, MET’S Institute of Engineering, Nashik, for his advice and support during the course of this work. I take this opportunity to thank Head of Department, Electronics & Telecommunication Engineering, Prof. Patil D. P. & express my gratitude towards my parents, colleagues and friends for their kind support during the completion of work.
Sarath Kolli TE(E&TC) Roll No.