Title page for 89521073


[Back to Results | New Search]

Student Number 89521073
Author Chin-Chih Wu(吳金池)
Author's Email Address No Public.
Statistics This thesis had been viewed 3386 times. Download 2877 times.
Department Electrical Engineering
Year 2001
Semester 2
Degree Master
Type of Document Master's Thesis
Language zh-TW.Big5 Chinese
Title The Research of Speaker Recognition System
Date of Defense 2002-06-04
Page Count 60
Keyword
  • speaker identification
  • speaker recognition
  • speaker verification
  • Abstract Abstract
    In recent years, the characteristics in human biology, such as the fingerprint, palm prints, eye and voice etc, were used to recognize personal identities. Among these biological characteristics, the human speech has the properties as easiness of product and extraction, as well as transmission through the network of telephone, and therefore suits for application of human identity.
    The Gaussian mixture model (GMM) is the most using statistical model for speaker recognition. In this plan, use the Gauss mixture model to represent each speaker distribute of feature vector. The covariance matrices can be full or diagonal matrices forms in GMM. Most of these models assume diagonal covariance matrices, but this assumes to ignore the each feature vectors correlation. If we assume the covariance matrix is diagonal form, we must use the orthonormal transformation to derive uncorrelated feature vectors. So that to reduce the relation of each vector of feature to lowest. This technique can improve the performance of speaker or speech recognition system.
    Table of Content 目錄
    摘要...........................Ⅰ
    致謝........................... Ⅱ
    目錄........................... Ⅲ
    附圖目錄.........................Ⅵ
    附表目錄.........................Ⅷ
    第一章 緒論.......................1
    1.1  研究動機.................... 1
    1.2  語者辨識系統概述................ 2
    1.3  適用於語者辨識的模型.............. 4
    1.4  語音資料庫................... 4
    1.5  章節概要.................... 5
    第二章 語音處理與語者辨識基本技術............6
    2.1  特徵參數擷取.................. 6
      2.2  語者模型................... . 9
         2.2.1 高斯混合語者模型.............. 9
         2.2.2 使用高斯混合模型的理由........... 11
    2.2.3 模型訓練與參數預估............. 12
    2.3  語者辨識方法..................17
    2.3.1 語者識別................. 17
    2.3.2 語者確認................. 17
       2.3.3 門檻值選取................18
    第三章 系統架構.....................19
    3.1  特徵參數之正交轉換...............20
    3.1.1 正交轉換之高斯混合模型延伸........ 22
    3.1.2 分散式之正交轉換.............. 23
    3.1.3 埋入式高斯混合模型............ 24
      3.2  向量量化高斯混合模型..............27
      3.2.1結合向量量化與特徵參數正交轉換...... 29
    3.3  雙重相似度計分方法...............32
    3.4  語者確認方法..................33
       3.4.1.1反語者模型(Anti-Speaker Model)....... 33
       3.4.1.2全域者模型(Global Speaker Model)...... 35
    第四章 語者辨識實驗.................. 37
    4.1  高斯混合模型系統設定實驗............ 37
    4.1.1 特徵參數階數的影響............ 37
    4.1.2 混合數的影響............... 38
    4.1.3 訓練語料長度的影響............. 41
      4.2  語者識別實驗..................42
    4.2.1 共變異矩陣形式的影響............ 42
    4.2.2 不同特徵參數轉換方式的比較......... 44
    4.2.3 傳統GMM與VQGMM的比較........ 46
    4.2.4 VQOGMM與其它轉換方式之比較結果..... 47
    4.2.5 雙重相似度計分方法的實驗結果....... 49
    4.3  語者確認實驗..................50
    4.3.1非正規化與正規化之語者確認實驗結果..... 50
    4.3.2 背景語者人數對系統的影響......... 52
    4.3.3 不同背景語者模型及測試語料長度對系統的影響53
    第五章 結論與未來展望.................56
    參考文獻.........................58
    Reference 參考文獻
    [ 1 ]G. R. Doddington, “Speaker recognition – identifying people by their voices”, Proc. IEEE, 73(11): 1651-1664, 1985.
    [ 2 ]S. Furui, “An overview of speaker recognition technology”, ESCA Workshop on Automatic Speaker Recognition, Identification and Verification, page 1-9, 1994.
    [ 3 ]Chung-Hsien Wu and Jau-Hung Chen, “Speech Activated Telephony Email Reader (SATER) Based on Speaker Verification and Text-To-Speech Conversion”, IEEE Trans. On Consumer Electronics, Vol. 43, No. 3, pp. 707-716, august 1997.
    [ 4 ]T. Jacobs and A. Setlur, “A Field Study of Performance Improvements in HMM-based Speaker verification”, Second IEEE Workshop on Interactive Voice Technology for Telecommunications Applications, pp. 121-124, 1994.
    [ 5 ]L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition, Prentice Hall, New Jersey, 1993.
    [ 6 ]B. H. Juang, “The past, present, and future of speech processing”, IEEE Signal Processing Magazine, page 24-48, May 1998.
    [ 7 ]John R. Deller, Jr., John G. Proakis, John H. L. Hansen, “Discrete-Time Processing of Speech Signals”, 1987.
    [ 8 ]D. A. Reynolds and R. C. Rose, “Robust Text-Independent Speaker Identification Using Gaussian Mixture Speaker Models”, IEEE Tran. On Speech and Audio Processing, 3(1): 72-83, January 1995.
    [ 9 ] G. McLachlan, Mixture Models. New York: Marcel Dekker, 1988.
    [10]Y. Linde, A. Buzo and R. M. Gray, “An Algorithm for the Vector Quantizer Design”, IEEE Transaction on Communication, Vol. 28, no. 4, pp. 84-95, Jan. 1980.
    [11]A. Dempster, N. Laird, and D. Rubin, “Maximum likelihood from incomplete data via the EM algorithm”, J. Royal Stat. Soc., Vol. 39, pp. 1-38, 1977.
    [12]D. A. Reynolds, “Speaker Identification and Verification Using Gaussian Mixture Speaker Models”, Speech Communication, Vol. 17, pp. 91-108, 1995.
    [13]D. A. Reynolds, R. C. Rose, and M. J. T. Smith, “PC-based TMS320C30 Implementation of Gaussian Mixture Model Text-independent Speaker Recognition System”, Proc. Internal. Conf. Signal Processing Applications and Technology, pp. 967-973, November 1992.
    [14] Li Liu and Jialong He, “On The Use of Orthogonal GMM In Speaker Recognition”, ICSLP 99.
    [15]Kuo-Hwei You, Hsiao-Chuan Wang, “Joint Estimation of Feature Transformation Parameters and Gaussian Mixture Model for Speaker Identification”, Speech Communication, 28:227-241, March 1999.
    [16] Q. Li, B.-H. Juang, Q. Zhou, and C.-H. Lee, ”Automatic Verbal Information Verification for User Authentication”, IEEE Trans. SAP, 8(5):585-602, 2000.
    [17] A. E. Rosenberg, J. Delong, C. H. Lee, B. H. Juang and F. K. Soong, ”The Use of Cohort Normalized Scores for Speaker Recognition”, Pro. ICSL 92. Banff, pp. 599-602. Oct. 1992.
    [18]Chi-Shi Liu, Hsiao-Chuan Wang and Chin-Hui Lee, “Speaker verification using normalized log-likelihood score”, IEEE Trans.on Speech and Audio Processing, Jan. 1996, pp. 57-60.
    [19]Y. Zhang, D. Zhang and Z. Shu, “A novel text-independent speaker verification method based on the global speaker model”, IEEE Trans. Systems, Man, and Cybernetics, 30(5):598-602, 2000.
    [20] 陳明熒, “PC電腦語音辨認實作”, 旗標出版有限公司,中華民國83年1月。
    Advisor
  • Yau-Tarng Juang(莊堯棠)
  • Files
  • 89521073.pdf
  • approve immediately
    Date of Submission 2002-06-05

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have dissertation-related questions, please contact with the NCU library extension service section.
    Our service phone is (03)422-7151 Ext. 57407,E-mail is also welcomed.