Research on voiceprint recognition system based on Gaussian Mixture Model

声明

Acknowledgements

Abstract

Table of contents

List of figures

List of tables

Chapter 1 Introduction

1．1 Research background and significance of voice print recognition

1．2 Research status of acoustic striation at home and abroad

1．3 Overview of voice print recognition

1．3．1 Introduction to voice print recognition

1．3．2 Classification of voice print recognition

1．4 Application of voice print recognition system in practice

1．5 The main work of this paper

Chapter 2 Speech signal processing

2．1 The mechanism of speech signal generation

2．2 Speech signal preprocessing

2．2．1 Voice signal sampling and quantization

2．2．2 Preemphasis of speech signal

2．2．3 Voice signals plus Windows

2．2．4 Endpoint detection for voice signals

2．3 The summary of this chapter

Chapter 3 Feature extraction of voice print recognition system

3．1 Common feature parameter extraction methods

3．2 Linear predictive cepstrum coefficient(LPCC)

3．2．1 Linear prediction coefficient(LPC)

3．2．2 Linear predictive cepstrum coefficient(LPCC)

3．3 Mel frequency cepstrum coefficient (MFCC) characteristic parameters extraction and analysis

3．3．1 Mel frequency cepstrum coefficient advantage analysis

3．3．2 Mel frequency cepstrum coefficient extraction method and process

3．3．3 Mel frequency cepstrum coefficients of the first and second order difference

3．4 The summary of this chapter

Chapter 4 Research on voice print recognition system based on GMM

4．1 Theoretical basis of GMM striation model

4．2 GMM mathematical model

4．2．1 GMM basic concept

4．2．2 The EM algorithm is used to estimate the GMM parameters

4．3 Voice print recognition system based on GMM model

4．4 The summary of this chapter

Chapter 5 Summary and Outlook

5．1 Summary

5．2 Outlook for the future

Bibliography

Appendix