跳到主要內容

臺灣博碩士論文加值系統

(44.201.97.224) 您好!臺灣時間:2024/04/18 03:19
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:鄭亦翔
研究生(外文):Yi-Hsiang Cheng
論文名稱:藉由調適性訊號正交化以完成盲蔽訊號源分離
論文名稱(外文):Blind Source Separation by Adaptive Signal Orthogonalization
指導教授:陳自強陳自強引用關係
指導教授(外文):Oscal T.-C. Chen
學位類別:碩士
校院名稱:國立中正大學
系所名稱:電機工程所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:中文
論文頁數:45
中文關鍵詞:獨立成份分析盲蔽訊號分離熵值估測前處理
外文關鍵詞:pre-processingentropy estimationblind source separationindependent component analysis
相關次數:
  • 被引用被引用:0
  • 點閱點閱:882
  • 評分評分:
  • 下載下載:10
  • 收藏至我的研究室書目清單書目收藏:0
音訊處理在今天已經是多媒體領域的一門重要學問,應用在音訊上的盲蔽訊號分離演算法亦佔有一席之地。傳統上,獨立成份分析與調適性盲蔽訊號分離已經廣為使用,特別是應用在特徵值擷取、資料分群(Data clustering)、語者辨識、影像分析等眾多領域。本論文主要是先介紹與獨立成份分析有關的數學模型以及相關假設,再來利用調適性正交化盲蔽訊號分離的原理,討論空間中由2個麥克風接收2個音源而來的混合訊號,分析當中不同的獨立成份並將其分離,最後再延伸至多維混合訊號的情形。在此使用m階間隔熵值估測演算法(m-spacing Entropy Estimation)來做為分離的演算法,並利用混合訊號的自相關函數進行不同的調適性白化前處理搭配,並以旋轉矩陣為更新學習機制,使預測的模型更加接近訊號源。此外,在進行白化程序前利用GSO正交化提早將獨立分量初步抽出,使後續的白化程序和分離演算法更有效率。
Nowadays, audio signal processing has become a critical technique in multimedia applications. Particularly, blind source separation plays an essential role in audio processing where independent component analysis and adaptive blind source separation are widely adopted in feature extraction, data clustering, speaker recognition and content analysis. This thesis first introduces the theoretical foundation with respect to independent component analysis. Second, the principle of adaptive signal orthogonalization is employed to explore 2 sound sources separated from the recorded signals. Additionally, the recorded signals from 2 and 4 mixtures of microphones are analyzed by using blind source separation. Finally, the proposed method is extensively investigated at the situation of multiple-dimension mixtures. Here, the m-spacing entropy estimator is utilized to determine independent components, and the auto-correlation characteristics of the mixtures are applied to conduct pre-whitening. Moreover, rotation matrices act as an adaptive learning mechanism to allow that our prediction model is closer to original sources. In order to efficiently computing independent component extraction, we applied Gram-Schmidt Orthogonalization (GSO) prior to pre-whitening to make the pr-processing and separation effectively.
誌謝辭 I
中文摘要 II
目錄 IV
圖目錄 VI
表目錄 VII
第一章 緒論 1
1.1 獨立成份分析簡介 1
1.2 研究動機與研究目的 3
1.3 論文架構 3
第二章 盲蔽訊號分離 4
2.1 前言 4
2.2 盲蔽訊號分離的問題敘述 4
2.2.1 未知訊號分離問題 4
2.2.2心理聽覺辨識能力對於盲蔽訊號分離的啟發 6
2.2.3 不確定性與非唯一解 6
2.3 盲蔽訊號分離的主要架構 6
2.4 資料前處理與相關數學模型 8
2.4.1資料前處理 8
2.4.2 盲蔽訊號分離之數學模型 10
2.5 獨立成份量測準則 13
2.5.1 最大概似法則演算法 14
2.5.2 最大熵值演算法 15
2.5.3 互消息演算法 15
第三章 調適性正交化盲蔽訊號分離演算法 17
3.1 前言 17
3.2 時域上以熵值估測為基礎的調適性正交化盲蔽訊號分離演算法 18
3.2.1 目標函數的推導 19
3.2.2 用於連續隨機變數之熵值估測 20
3.2.3 二維分離演算法說明與討論 26
3.2.4 多維分離演算法說明與討論 28
第四章 實驗結果與討論 30
4.1 改善分離效能之方案 30
4.1.1 Gram-Schmidt正交化 30
4.1.2 調適性白化機制 32
4.2 實驗結果 34
4.2.2 模擬實驗環境 35
4.2.1 兩音源訊號由兩麥克風收錄 36
4.2.2 兩音源訊號由四麥克風收錄 38
第五章 結論與未來工作 41
參考文獻 42
附錄A 混合訊號與輸出訊號自相關函數的推導 45
[1] P. Comon, “Independent component analysis, a new concept?” Signal Processing, vol. 36, no. 3, pp. 287-314, 1994.
[2] A. Belouchrani, K. Abed-Meraim, J.-F. Cardoso and E. Moulines, “A blind source separation technique using second-order statistics,” IEEE Tans. on Acoustics, Speech, and Signal Processing, vol. 45, pp. 434-444, 1997.
[3] A. Cichocki and S. Amari, Adaptive Blind Signal and Image Processing, 1st ed. New York: Wiley, 2003.
[4] L. Tong, V.C. Soon, Y.F. Huang, and R. Liu, “AMUSE: a new blind identification algorithm,” Proc. of IEEE Int. Symp. Circuits Syst., New Orleans, LA, pp. 1784–1787, May. 1990.
[5] L. Tong, V. C. Soon, Y. F. Huang and R. Liu, “Blind identification of source signals,” IEEE Trans. on Acoustics. Speech, and Signal Processing, vol. 38, no.5, pp.499-509, 1991.
[6] A. Hyvärinen, J. Karhunen and E. Oja, Independent Component Analysis, New York: Wiley & Sons, Inc., 2001.
[7] T. M. Cover and J. A. Thomas, Elements of Information Theory, New York: Wiley, 1991.
[8] A. Hyvärinen “Fast and robust fixed-point algorithms for independent component analysis.” IEEE Transactions on Neural Networks, vol. 10, no.3, pp. 626-634, 1999.
[9] L. Molgedey and H.G. Schuster, “Separation of a mixture of independent signals using time delayed correlations,” Physical Review Letters, vol. 72, pp. 3634-3636, 1994.
[10] L. Tong, R.-W. Liu, V. C. Soon and Y.-F. Huang, “Indeterminacy and identifiability of blind identification,” IEEE Trans. on Circuits and Systems, vol. 38, pp. 499-509, 1991.
[11] E. Weinstein, M. Feder and A. Oppenheim, “Multi-channel signal separation by decorrelation,” IEEE Trans. on Speech and Audio Processing, vol 1, no. 4, pp. 405-413, Oct. 1993.
[12] S. Van Gerven and D. Van Compernolle,“Signal separation by symmetric adaptive decorrelation: stability, convergence, and uniqueness,” IEEE Trans. on Signal Processing, vol. 43, no. 7, pp. 1602-1612, 1995.
[13] J.-F. Cardoso and A. Souloumiac, “Jacobi angles for simultaneous diagonalization,” SIAM J. Mat. Anal. Appl., vol. 17, no. 1, pp. 161-164, Jan. 1996.
[14] S. Ikeda and N. Murata, “An approach to blind source separation of speech signals,” Proc. of IEEE Int. Symposium on Nonlinear Theory and its Applications, Crans-Montana, Switzerland, pp. 261-264,1998.
[15] L. Parra and C. Spence, “Convolutive blind source separation of non-stationary sources,” IEEE Trans. on Speech and Audio Processing, pp. 320-327, May 2000.
[16] A. Hyvärinen, “Blind source separation by nonstationarity of variance: A cumulant-based approach,” IEEE Tans. on Neural Networks, vol. 12, no.6, pp. 1471-1474, 2001.
[17] R. Bach and M. I. Jordan, “Kernel independent component analysis,” Journal of Machine Learning Research, vol. 3, pp. 1–48, 2002.
[19] A. Benveniste, M. Goursat and G. Ruget, “Robust identification of a nonminimum phase system:blind adjustment of a linear equalizer in data communications,” IEEE Trans on Automatic Control, vol. 25, no.3, pp.385–99, 1980.
[20] E. Shannon, “The mathematical theory of communication,” The Bell System Technical Journal, vol. 27, pp. 379–423,623–656, Oct. 1948.
[21] S. Kullback, Information Theory and Statistics, New York: John Wiley and Sons, 1959.
[22] T. Lee, M. Girolami, A. Bell and T. Sejnowski, “A unifying information-theoretic framework for independent component analysis,” International Journal on Mathematical and Computer Modeling, 1999.
[23] O. Vasicek, “A test for normality based on sample entropy,” Journal of the Royal Statistical Society, Series B, vol. 38, no. 1, pp. 54–59, 1976.
[24] J. Beirlant, E. J. Dudewicz, L. Gy¨orfi, and E. C. van der Meulen, “Nonparametric entropy estimation: an overview,” International Journal of Mathematical and Statistical Sciences, vol. 6, no. 1, pp. 17–39, June 1997.
[25] Hyvärinen, “New approximations of differential entropy for independent component analysis and projection pursuit,” Advances in Neural Information Processing Systems 10, pp. 273–279, 1997.
[26] C. Arnold, N. Balakrishnan and H.N. Nagaraja, A First Course in Order Statistics, New York: John Wiley and Sons, 1992.
[27] E. G. L. –Miller and J. W. Fisher III, “ICA Using Spacings Estimates of Entropy,” Journal of Machine Learning Research, vol. 4, pp. 1271-1295, 2003
[28] H. Golub and C. F. Van Loan, Matrix Computations, Johns Hopkins University Press, 1996.
[29] R. Boscolo, H. Pan and V. P. Roychowdhury, “Independent component analysis based on non-parametric density estimation,” IEEE Trans. on Neural Networks, vol. 15, no. 1, pp. 55-65, 2004.
[30] Avalible, http://www.cis.hut.fi/projects/ica/fastica/index.shtml.
[31] Avalible, http://www.ee.ucla.edu/~riccardo/ICA/npica.html.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊