独立分量分析及其在语音识别预处理中的应用
|
摘要
独立分量分析(ICA)是一种高阶统计量信号处理方法,1995年以来逐渐被广泛接受,越来越多地被应用于与信号处理有关的领域。目前,独立分量分析是模式识别与信号处理等相关领域的一个重要的研究热点。本文旨在研究基于独立分量分析的盲信号处理(BSP)理论及其在语音识别预处理中语音信号盲源分离(BSS)和语音增强等方面的应用。目的是寻求一种稳健的语音识别预处理手段。
本文在讨论独立分量分析理论,重点研究了被广泛应用的FastICA算法的基础上,做了如下三个方面的研究工作:
探讨了用不同的线性ICA算法实现的混叠语音盲分离,并主观和客观等不同角度评价用ICA方法对这些混叠信号的分离效果和算法的分离性能,另外,本文实现了一类单信道的盲分离问题的简单解决方案,它可以只用一个信道就能从被噪声污染的信号中把较纯净的语音提取出来,而传统方法至少需要两个信道。
基于高斯白噪声背景,本文比较了传统算法和基于ICA/BSS算法在语音消噪和增强方面的差异,指出了基于ICA方法在高噪声环境下的优越性,并且指出在较大的信噪比范围内基于此方法的消噪的效果具有一定的平稳性,接着,本文讨论了ICA方法对多种不同环境噪声的适应性问题。此外,文章还提出了一种基于ICA与小波的联合降噪方法,试验表明,这种方法能使得语音增强性能进一步提高。
文章最后,用DTW的方法实现了一个简单的非特定人连接词智能家居语音识别系统,基于这个系统本文设计了一系列的试验,试验证明在恶劣的环境下,基于ICA的预处理方法能够使系统的识别性能得到很大的提高。
总之,不论从混叠语音的盲分离,还是从语音增强效果,乃至系统识别率的提高等不同角度来看,独立分量分析都不失为一种有效的语音识别预处理方法。本文的研究将对噪声环境特别是高环境噪声下的语音分析与识别具有积极的意义。
ICA is a higher-order statistics tool. From 1995, it has been more and more widely recognized and applied in diverse sub-fields of signal processing domain. Nowadays it is an important and indispensable research frontier in correlative fields of pattern recognition and signal processing. This paper is mainly engaged in the research of BSP theory based on ICA and its application in blind speech signal separation and speech enhancement for the preprocessing of speech recognition, attempting to secure some robust measurement of speech recognition.
ICA theory is discussed in the paper, especially noted the Fast-ICA algorithms which has been widely recognized. Based on which, we did three aspects research as follows:
This paper makes an attempt to apply these ICA algorithms in speech signal blind separation. For evaluating the performance of separating pure speech signal from mixed speech signal by ICA, we propose some subjective and some objective measures. In addition, we also implement an algorithm that can acquire pure speech signal from mixed speech signal by a single channel, traditionally ICA needing at least two signal channels.
Upon comparing ICA with classical de-noising algorithms, we find out ICA precedes classical algorithms if intensive environmental noise presents, also ICA shows notable stabilization for vast SNR range. Although above results are driven from speech signal entangled with intense Gaussian whiten noise, their applicability also discussed in many other different noise environment. Furthermore, we propose a united de-noising algorithm based on ICA and wavelet. Tentative tests show that this united method holding more powerful speech enhancement capability.
Finally, we implement a preliminary intelligent household conjunctive words speech recognition system, based on which we design a series of examinations. The results indicate that the preprocessing methods based ICA can enhance the recognition capability of the system.
In conclusion,not only from the blind source separation of mixing speech, but also from the performance of speech enhancement or from the advance the recognition ratio of system, ICA is indeed an kind of efficiency methods for speech recognition preprocessing. The study of this paper will have positive meanings to speech analysis and recognition under noising environment, especially under intensive environment noise.
本文在讨论独立分量分析理论,重点研究了被广泛应用的FastICA算法的基础上,做了如下三个方面的研究工作:
探讨了用不同的线性ICA算法实现的混叠语音盲分离,并主观和客观等不同角度评价用ICA方法对这些混叠信号的分离效果和算法的分离性能,另外,本文实现了一类单信道的盲分离问题的简单解决方案,它可以只用一个信道就能从被噪声污染的信号中把较纯净的语音提取出来,而传统方法至少需要两个信道。
基于高斯白噪声背景,本文比较了传统算法和基于ICA/BSS算法在语音消噪和增强方面的差异,指出了基于ICA方法在高噪声环境下的优越性,并且指出在较大的信噪比范围内基于此方法的消噪的效果具有一定的平稳性,接着,本文讨论了ICA方法对多种不同环境噪声的适应性问题。此外,文章还提出了一种基于ICA与小波的联合降噪方法,试验表明,这种方法能使得语音增强性能进一步提高。
文章最后,用DTW的方法实现了一个简单的非特定人连接词智能家居语音识别系统,基于这个系统本文设计了一系列的试验,试验证明在恶劣的环境下,基于ICA的预处理方法能够使系统的识别性能得到很大的提高。
总之,不论从混叠语音的盲分离,还是从语音增强效果,乃至系统识别率的提高等不同角度来看,独立分量分析都不失为一种有效的语音识别预处理方法。本文的研究将对噪声环境特别是高环境噪声下的语音分析与识别具有积极的意义。
ICA is a higher-order statistics tool. From 1995, it has been more and more widely recognized and applied in diverse sub-fields of signal processing domain. Nowadays it is an important and indispensable research frontier in correlative fields of pattern recognition and signal processing. This paper is mainly engaged in the research of BSP theory based on ICA and its application in blind speech signal separation and speech enhancement for the preprocessing of speech recognition, attempting to secure some robust measurement of speech recognition.
ICA theory is discussed in the paper, especially noted the Fast-ICA algorithms which has been widely recognized. Based on which, we did three aspects research as follows:
This paper makes an attempt to apply these ICA algorithms in speech signal blind separation. For evaluating the performance of separating pure speech signal from mixed speech signal by ICA, we propose some subjective and some objective measures. In addition, we also implement an algorithm that can acquire pure speech signal from mixed speech signal by a single channel, traditionally ICA needing at least two signal channels.
Upon comparing ICA with classical de-noising algorithms, we find out ICA precedes classical algorithms if intensive environmental noise presents, also ICA shows notable stabilization for vast SNR range. Although above results are driven from speech signal entangled with intense Gaussian whiten noise, their applicability also discussed in many other different noise environment. Furthermore, we propose a united de-noising algorithm based on ICA and wavelet. Tentative tests show that this united method holding more powerful speech enhancement capability.
Finally, we implement a preliminary intelligent household conjunctive words speech recognition system, based on which we design a series of examinations. The results indicate that the preprocessing methods based ICA can enhance the recognition capability of the system.
In conclusion,not only from the blind source separation of mixing speech, but also from the performance of speech enhancement or from the advance the recognition ratio of system, ICA is indeed an kind of efficiency methods for speech recognition preprocessing. The study of this paper will have positive meanings to speech analysis and recognition under noising environment, especially under intensive environment noise.
引文
[1] A Hyv?rinen, et al. Independent Component Analysis [M]. Wiley and Sons, 2001.
[2] A Cichocki, et al. 自适应盲信号与图像处理 [M].北京:电子工业出版社,2005.
[3] 杨福生,等. 独立分量分析的原理与应用 [M].北京:清华大学出版社,2006.
[4] 杨行峻,等. 人工神经网络与盲信号处理 [M].北京:清华大学出版社,2003.
[5] S Haykin. 神经网络综合基础(影印版)[M].北京:清华大学出版社,2001.
[6] 胡广书. 数字信号处理:理论、算法与应用(第二版) [M].北京:清华大学出版社,2003.
[7] 张贤达. 代信号处理 [M].北京:清华大学出版社,2002
[8] 邱天爽. 统计信号处理:非高斯信号及其应用 [M].北京:电子工业出版社,2004.
[9] L B Almeida. Linear and nonlinear ICA based on mutual information—the MISEP method [J]. Signal Processing, 84(2004):231-245.
[10] A R Webb. Statistical Pattern Recognition (Second Edition) [M]. John Wiley &Sons,2002.
[11] 吴响蓉.模式分类特征提取中的独立分量分析 [D].桂林:广西师范大学,2004.
[12] 高隽.智能信息处理导论 [M].北京:机械工业出版社,2004.
[13] C Jutten. Blind separation of sources, Part I: An adaptive algorithm based on euro-mimetic architecture [J]. Signal Processing, 24(1991):1-10.
[14] P Comon. Blind separation of sources, Part II: Problems statement [J]. Signal Processing, 24(1991):11-20.
[15] E Sorouchyari. Blind separation of sources, Part III: Stability analysis [J]. Signal Processing, 24(1991):21 -29.
[16] Lee Te-won, et al. Independent component analysis using an extended infomax algorithm for Mixed Subgaussian and Supergaussian Sources [J], Neural computation, 1999,11(2):409-433.
[17] 李小军,等.盲信号分离研究分类与展望 [J].西安电子科技大学学报(自然科学版), 2004.31(3):399-405.
[18] Jang Gil-Jin, et al. Single-channel signal separation using time-domain basis functions [J]. IEEE Signal Processing Letters, 2003,10(6):168-171.
[19] J F Cardoso. Blind signal separation: Statistical principles [J]. Proceedings of the IEEE. 1998,86(10):2009 -2026.
[20] P Comon. Independent component analysis, A new concept? [J]. Signal Processing, 36 (1994):287-314.
[21] A J Bell, et al. A non-linear information maximization algorithm that performs blind separation [J]. In Advances in Neural Information Processing Systems, 1995(7):467–474.
[22] A J Bell, et al. An information-maximization approach to blind separation and blind deconvolution [J]. Neural Computation, 1995(7):1129–1159.
[23] Te-won Lee. Independent Component Analysis [M]. Kluwer Academic Press, 1998.
[24] S Roberts, et al. Independent Component Analysis: Principle and Practice [M]. Cambridge University Press, 2001.
[25] M Girolami, et al. Advances in Independent Component Analysis[M]. Springer,2000.
[26] M Girolami. Self-organizing Neural Networks: Independent Component Analysis and Blind Source Separation [M]. Springer-Verlag London Limited, 1999.
[27] Simon Haykin ed..Unsupervised adaptive filtering, Vol.1, Blind Source Separation. & Vol. 2, Blind Deconvolution [M]. John Wiley and Sons, 2000.
[28] J V Stone. Independent Component Analysis: A Tutorial Introduction [M]. MIT Press, 2004.
[29] Gustavo Deco. An Information Theoretic Approach to Neural Computing [M]. New York: Springer, 1996.
[30] 张贤达.时间序列分析:高阶统计量方法 [M].北京:清华大学出版社,1996.
[31] A Cichocki, et al. Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications[M]. John Wiley and Sons, 2002.
[32] A Hyv?rinen, et al. Independent component analysis: algorithms and applications [J].Neural Networks, 13(2000):411-430.
[33] A J Bell, et al. Independent Component Analyses, Wavelets, and Neural Networks [M]. SPIE, 2003.
[34] A Hyv?rinen. Fast and robust fixed-point algorithms for independent component analysis [J]. IEEE Trans. on Neural Networks, 1999,10(3):626-634.
[35] Yi-fan Gong, Speech recognition on noisy Environments: A survey [J]. Speech Communication, 1995,16 (1): 261-291.
[36] http://inc2.ucsd.edu/~tewon/Blind/blind_audio.html[DB/OL]
[37] 张雄伟,等.现代语音处理技术及应用 [M].北京:机械工业出版社,2003.
[38] J M Mendel. Tutorial on higher-order statistics (spectra) in signal processing and system theory Theoretical results and some applications [J]. Proceedings of the IEEE, 1991,79(3):278-306.
[39] 黄炳锡,等.实用语音识别基础 [M].北京:国防工业大学出版社,2005.
[40] 吕瑞兰.小波阈值去噪的性能分析及基于能量元的小波阈值去噪方法研究 [D].杭州:浙江大学, 2003.
[41] 韩仲志,等.强噪声环境下基于ICA/BSS的语音识别预处理方法 [J].云南大学学报,2005,27(5 A):255-259.
[42] 韩仲志,等.基于ICA/BSS的高噪下语音增强研究 [J].广西师范大学学报,2005,(1):189-193.
[43] 叶洪涛,等.基于改进型DTW的语音拨号模拟 [J].广西物理,2005,26(1):13-15.
[44] http://spib.ece.rice.edu/spib/directory.html[DB/OL]
[45] 张海成.现代自动识别技术及应用 [M].北京:清华大学出版社,2003.
[46] L Rabiner, et al. 语音识别基本原理(影印版)[M].清华大学出版社,1999.
[47] T H Hwang, et al. Cepstral behavior due to additive noise and a compensation scheme for nois8speech recognition [J]. IEEE Proceedings on Vision, Image and Signal Processing, 145(1998).
[48] A D Back, et al. A First Application of Independent Component Analysis to Extracting Structure from Stock Returns [C]. International Journal of Neural Systems, Vol. 8, No.5 (October, 1997).
[49] H G Okuno, et al. Effects of increasing modalities in recognizing three simultaneous speeches[J].Speech Communication, 43(2004):347-359.
[50] O Déniz, et al. Face recognition using independent component analysis and support vector machines [J]. Pattern Recognition Letters, 24(2003):2153-2157.
[51] K Torkkola. Feature Extraction by Non-Parametric Mutual Information Maximization [J]. Journal of Machine Learning Research, 3(2003):1415-1438.
[52] M J Mckeown, et al. Spatially independent activity patterns in functional MRI data during the Stroop color-naming task [C]. Proc. Natl. Acad. Sci. USA, Vol.95, No.803 (February, 1998).
[53] H G Kim, et al. Speaker Recognition Using MPEG-7 Descriptors [R]. Submitted to Euro-speech 2003 Switzerland, (September, 2003).
[54] U M Bae,et al. Top-down attention to complement independent component analysis for blind signal separation [J]. Neuro-computing, 49(2002):315-327.
[55] D E Callan,et al. Multi-modal contribution to speech perception revealed by independent component analysis: a single-sweep EEG case study [J]. Cognitive Brain Research, 10(2001):349-353.
[56] M Haritopoulos, et al. Image de-noising using self-organizing map-based nonlinear independent component analysis [J]. Neural Networks, 15(2002):1085-1098.
[57] O W Kwon, et al. Phoneme recognition using ICA-based feature extraction and transformation [J]. Signal Processing, 84(2004):1005-1019.
[58] http://bbs.matwav.com [EB/OL].
[59] T K Kim, et al. Independent component analysis in a local facial residue space for face recognition [J] Pattern Recognition, 37(2004):1873-1885.
[60] T W Lee, et al. Blind Source Separation of More Sources Than Mixtures Using Over-complete Representations [J]. IEEE signal processing letters, 6(1999).
[61] A Hyv?ainen, et al. Nonlinear independent component analysis: Existence and uniqueness results[J]. Neural Networks, 12(1999):429-439.
[62] 赵鹤鸣,等.小波变换在噪声环境下语音识别中的应用 [J].苏州大学学报,1998,14(4):31-35.
[63] 冯大政,等.信号盲分离问题多阶段分解算法 [J].自然科学进展,2002,12(3):324-329.
[64] 陈阳,等.一类新的独立性度量及其在盲信号分离中的应用 [J].武汉大学学报,2004,29(1):84-89.
[65] 杨红卫,等.一种改进的基于 ICA 的信号增强方法 [J].电声技术, 2003,(7):15-18.
[66] 张旭秀,等.独立分量分析原理及其应用 [J].大连铁道学院学报,2003,26(2):64-70.
[67] 刘庆华,等.基于 DSP 的发送端语音降噪技术的实现 [J].噪声技术,2004,(4):61-63.
[68] 杨红卫,等.基于 ICA 的周期性噪声消除算法 [J].计算机研究与发展.2004,41(11):2012-2019.
[69] 刘盛鹏,等.基于 TMS320C64xDSPBIOSⅡ嵌入式语音采集与盲分离系统设计 [J].电子技术,2004(4):17-21.
[70] 刘盛鹏,等.基于 TMS320C64xDSP 的语音采集与盲信号分离系统设计 [J].电子设计与应用,2004(4):92-93.
[71] 孔薇,等.基于独立成分分析的强背景噪声去噪方法 [J].上海交通大学学报,2004,38(12):1958-1963.
[72] 史玉峰.基于独立分量分析的变形子模式识别与分离 [J].金属矿山,2005,346(4):46-50.
[73] 吴小培,等.基于独立分量分析的混合声音信号分离 [J].中国科学技术大学学报,2001,31(1):68-74.
[74] 吴微东,等.基于盲源分离的一种快速独立分量分析算法 [J].汕头大学学报,2004,19(2):58-63.
[75] 王刚,等.于时间序列预测的独立分量排序 [J].国防科技大学学报,2005,27(5):78-82.
[76] 张德洁,等.基于统计信息的两类盲信号分离方法之比较 [J].医学信息,2005,18(6):587-590.
[77] 游荣义,等.基于小波变换的盲信号分离的神经网络方法[J].仪器仪表学报,2005.26(4):415-418.
[78] 章晋龙,等.基于遗传算法的有序盲信号提取 [J].电子学报,2004,32(4):616-619.
[79] 丁沛,等.基于语音增强失真补偿的抗噪声语音识别技术 [J].中文信息学报,2004,18(5):64-69.
[80] 张旭秀,等.基于源信号统计独立性 ICA 的不确定性研究 [J].系统工程与电子技术,2004,26(4):556-559.
[81] 张旭秀,等.基于源信号之间统计独立性 ICA 方法的等价性研究 [J].探测与控制学报,2003,25(4):21-25.
[82] 肖明,等.卷积混叠盲信号分离的一种线性化方法 [J].华南理工大学学报,2005,33(3):34-39.
[83] 张贤达,等.盲信号分离 [J].电子学报,2001,29(12A):1766-1772
[84] 屈微,等.拓扑独立分量分析在方言特征提取中的应用研究 [J].语音技术,2005,(5):39-43.
[85] 姚文冰.稳健语音识别技术发展现状及展望 [J].信号处理,2001,17(6):454-465.
[86] V D Sánchez, et al. Frontiers of research in BSS/ICA [J]. Neuro-computing, 49(2002):7–23.
[87] 焦卫东,等.基于独立分量分析的噪声消除技术研究 [J].浙江大学学报(工学版),2004,38(7):872-889.
[88] 彭煊,等.基于独立分量分析的语音增强 [J].信号处理,2002,18(5):477-479.
[2] A Cichocki, et al. 自适应盲信号与图像处理 [M].北京:电子工业出版社,2005.
[3] 杨福生,等. 独立分量分析的原理与应用 [M].北京:清华大学出版社,2006.
[4] 杨行峻,等. 人工神经网络与盲信号处理 [M].北京:清华大学出版社,2003.
[5] S Haykin. 神经网络综合基础(影印版)[M].北京:清华大学出版社,2001.
[6] 胡广书. 数字信号处理:理论、算法与应用(第二版) [M].北京:清华大学出版社,2003.
[7] 张贤达. 代信号处理 [M].北京:清华大学出版社,2002
[8] 邱天爽. 统计信号处理:非高斯信号及其应用 [M].北京:电子工业出版社,2004.
[9] L B Almeida. Linear and nonlinear ICA based on mutual information—the MISEP method [J]. Signal Processing, 84(2004):231-245.
[10] A R Webb. Statistical Pattern Recognition (Second Edition) [M]. John Wiley &Sons,2002.
[11] 吴响蓉.模式分类特征提取中的独立分量分析 [D].桂林:广西师范大学,2004.
[12] 高隽.智能信息处理导论 [M].北京:机械工业出版社,2004.
[13] C Jutten. Blind separation of sources, Part I: An adaptive algorithm based on euro-mimetic architecture [J]. Signal Processing, 24(1991):1-10.
[14] P Comon. Blind separation of sources, Part II: Problems statement [J]. Signal Processing, 24(1991):11-20.
[15] E Sorouchyari. Blind separation of sources, Part III: Stability analysis [J]. Signal Processing, 24(1991):21 -29.
[16] Lee Te-won, et al. Independent component analysis using an extended infomax algorithm for Mixed Subgaussian and Supergaussian Sources [J], Neural computation, 1999,11(2):409-433.
[17] 李小军,等.盲信号分离研究分类与展望 [J].西安电子科技大学学报(自然科学版), 2004.31(3):399-405.
[18] Jang Gil-Jin, et al. Single-channel signal separation using time-domain basis functions [J]. IEEE Signal Processing Letters, 2003,10(6):168-171.
[19] J F Cardoso. Blind signal separation: Statistical principles [J]. Proceedings of the IEEE. 1998,86(10):2009 -2026.
[20] P Comon. Independent component analysis, A new concept? [J]. Signal Processing, 36 (1994):287-314.
[21] A J Bell, et al. A non-linear information maximization algorithm that performs blind separation [J]. In Advances in Neural Information Processing Systems, 1995(7):467–474.
[22] A J Bell, et al. An information-maximization approach to blind separation and blind deconvolution [J]. Neural Computation, 1995(7):1129–1159.
[23] Te-won Lee. Independent Component Analysis [M]. Kluwer Academic Press, 1998.
[24] S Roberts, et al. Independent Component Analysis: Principle and Practice [M]. Cambridge University Press, 2001.
[25] M Girolami, et al. Advances in Independent Component Analysis[M]. Springer,2000.
[26] M Girolami. Self-organizing Neural Networks: Independent Component Analysis and Blind Source Separation [M]. Springer-Verlag London Limited, 1999.
[27] Simon Haykin ed..Unsupervised adaptive filtering, Vol.1, Blind Source Separation. & Vol. 2, Blind Deconvolution [M]. John Wiley and Sons, 2000.
[28] J V Stone. Independent Component Analysis: A Tutorial Introduction [M]. MIT Press, 2004.
[29] Gustavo Deco. An Information Theoretic Approach to Neural Computing [M]. New York: Springer, 1996.
[30] 张贤达.时间序列分析:高阶统计量方法 [M].北京:清华大学出版社,1996.
[31] A Cichocki, et al. Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications[M]. John Wiley and Sons, 2002.
[32] A Hyv?rinen, et al. Independent component analysis: algorithms and applications [J].Neural Networks, 13(2000):411-430.
[33] A J Bell, et al. Independent Component Analyses, Wavelets, and Neural Networks [M]. SPIE, 2003.
[34] A Hyv?rinen. Fast and robust fixed-point algorithms for independent component analysis [J]. IEEE Trans. on Neural Networks, 1999,10(3):626-634.
[35] Yi-fan Gong, Speech recognition on noisy Environments: A survey [J]. Speech Communication, 1995,16 (1): 261-291.
[36] http://inc2.ucsd.edu/~tewon/Blind/blind_audio.html[DB/OL]
[37] 张雄伟,等.现代语音处理技术及应用 [M].北京:机械工业出版社,2003.
[38] J M Mendel. Tutorial on higher-order statistics (spectra) in signal processing and system theory Theoretical results and some applications [J]. Proceedings of the IEEE, 1991,79(3):278-306.
[39] 黄炳锡,等.实用语音识别基础 [M].北京:国防工业大学出版社,2005.
[40] 吕瑞兰.小波阈值去噪的性能分析及基于能量元的小波阈值去噪方法研究 [D].杭州:浙江大学, 2003.
[41] 韩仲志,等.强噪声环境下基于ICA/BSS的语音识别预处理方法 [J].云南大学学报,2005,27(5 A):255-259.
[42] 韩仲志,等.基于ICA/BSS的高噪下语音增强研究 [J].广西师范大学学报,2005,(1):189-193.
[43] 叶洪涛,等.基于改进型DTW的语音拨号模拟 [J].广西物理,2005,26(1):13-15.
[44] http://spib.ece.rice.edu/spib/directory.html[DB/OL]
[45] 张海成.现代自动识别技术及应用 [M].北京:清华大学出版社,2003.
[46] L Rabiner, et al. 语音识别基本原理(影印版)[M].清华大学出版社,1999.
[47] T H Hwang, et al. Cepstral behavior due to additive noise and a compensation scheme for nois8speech recognition [J]. IEEE Proceedings on Vision, Image and Signal Processing, 145(1998).
[48] A D Back, et al. A First Application of Independent Component Analysis to Extracting Structure from Stock Returns [C]. International Journal of Neural Systems, Vol. 8, No.5 (October, 1997).
[49] H G Okuno, et al. Effects of increasing modalities in recognizing three simultaneous speeches[J].Speech Communication, 43(2004):347-359.
[50] O Déniz, et al. Face recognition using independent component analysis and support vector machines [J]. Pattern Recognition Letters, 24(2003):2153-2157.
[51] K Torkkola. Feature Extraction by Non-Parametric Mutual Information Maximization [J]. Journal of Machine Learning Research, 3(2003):1415-1438.
[52] M J Mckeown, et al. Spatially independent activity patterns in functional MRI data during the Stroop color-naming task [C]. Proc. Natl. Acad. Sci. USA, Vol.95, No.803 (February, 1998).
[53] H G Kim, et al. Speaker Recognition Using MPEG-7 Descriptors [R]. Submitted to Euro-speech 2003 Switzerland, (September, 2003).
[54] U M Bae,et al. Top-down attention to complement independent component analysis for blind signal separation [J]. Neuro-computing, 49(2002):315-327.
[55] D E Callan,et al. Multi-modal contribution to speech perception revealed by independent component analysis: a single-sweep EEG case study [J]. Cognitive Brain Research, 10(2001):349-353.
[56] M Haritopoulos, et al. Image de-noising using self-organizing map-based nonlinear independent component analysis [J]. Neural Networks, 15(2002):1085-1098.
[57] O W Kwon, et al. Phoneme recognition using ICA-based feature extraction and transformation [J]. Signal Processing, 84(2004):1005-1019.
[58] http://bbs.matwav.com [EB/OL].
[59] T K Kim, et al. Independent component analysis in a local facial residue space for face recognition [J] Pattern Recognition, 37(2004):1873-1885.
[60] T W Lee, et al. Blind Source Separation of More Sources Than Mixtures Using Over-complete Representations [J]. IEEE signal processing letters, 6(1999).
[61] A Hyv?ainen, et al. Nonlinear independent component analysis: Existence and uniqueness results[J]. Neural Networks, 12(1999):429-439.
[62] 赵鹤鸣,等.小波变换在噪声环境下语音识别中的应用 [J].苏州大学学报,1998,14(4):31-35.
[63] 冯大政,等.信号盲分离问题多阶段分解算法 [J].自然科学进展,2002,12(3):324-329.
[64] 陈阳,等.一类新的独立性度量及其在盲信号分离中的应用 [J].武汉大学学报,2004,29(1):84-89.
[65] 杨红卫,等.一种改进的基于 ICA 的信号增强方法 [J].电声技术, 2003,(7):15-18.
[66] 张旭秀,等.独立分量分析原理及其应用 [J].大连铁道学院学报,2003,26(2):64-70.
[67] 刘庆华,等.基于 DSP 的发送端语音降噪技术的实现 [J].噪声技术,2004,(4):61-63.
[68] 杨红卫,等.基于 ICA 的周期性噪声消除算法 [J].计算机研究与发展.2004,41(11):2012-2019.
[69] 刘盛鹏,等.基于 TMS320C64xDSPBIOSⅡ嵌入式语音采集与盲分离系统设计 [J].电子技术,2004(4):17-21.
[70] 刘盛鹏,等.基于 TMS320C64xDSP 的语音采集与盲信号分离系统设计 [J].电子设计与应用,2004(4):92-93.
[71] 孔薇,等.基于独立成分分析的强背景噪声去噪方法 [J].上海交通大学学报,2004,38(12):1958-1963.
[72] 史玉峰.基于独立分量分析的变形子模式识别与分离 [J].金属矿山,2005,346(4):46-50.
[73] 吴小培,等.基于独立分量分析的混合声音信号分离 [J].中国科学技术大学学报,2001,31(1):68-74.
[74] 吴微东,等.基于盲源分离的一种快速独立分量分析算法 [J].汕头大学学报,2004,19(2):58-63.
[75] 王刚,等.于时间序列预测的独立分量排序 [J].国防科技大学学报,2005,27(5):78-82.
[76] 张德洁,等.基于统计信息的两类盲信号分离方法之比较 [J].医学信息,2005,18(6):587-590.
[77] 游荣义,等.基于小波变换的盲信号分离的神经网络方法[J].仪器仪表学报,2005.26(4):415-418.
[78] 章晋龙,等.基于遗传算法的有序盲信号提取 [J].电子学报,2004,32(4):616-619.
[79] 丁沛,等.基于语音增强失真补偿的抗噪声语音识别技术 [J].中文信息学报,2004,18(5):64-69.
[80] 张旭秀,等.基于源信号统计独立性 ICA 的不确定性研究 [J].系统工程与电子技术,2004,26(4):556-559.
[81] 张旭秀,等.基于源信号之间统计独立性 ICA 方法的等价性研究 [J].探测与控制学报,2003,25(4):21-25.
[82] 肖明,等.卷积混叠盲信号分离的一种线性化方法 [J].华南理工大学学报,2005,33(3):34-39.
[83] 张贤达,等.盲信号分离 [J].电子学报,2001,29(12A):1766-1772
[84] 屈微,等.拓扑独立分量分析在方言特征提取中的应用研究 [J].语音技术,2005,(5):39-43.
[85] 姚文冰.稳健语音识别技术发展现状及展望 [J].信号处理,2001,17(6):454-465.
[86] V D Sánchez, et al. Frontiers of research in BSS/ICA [J]. Neuro-computing, 49(2002):7–23.
[87] 焦卫东,等.基于独立分量分析的噪声消除技术研究 [J].浙江大学学报(工学版),2004,38(7):872-889.
[88] 彭煊,等.基于独立分量分析的语音增强 [J].信号处理,2002,18(5):477-479.