Blind Source Separation and Estimation Methods for Nonlinear Convoltive Mixtures

非线性卷积混合的盲源分离和估计方法

• 批准号: 15560323
• 负责人: NAKAYAMA Kenji
• 金额: $ 2.37万
• 依托单位: Kanazawa University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2003
• 资助国家: 日本
• 起止时间: 2003 至 2004
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-15560323/
• 关键词: Signal source separation; Mixture process; Nonlinear; Learning algorithm; Signal distortion; Feedforward; Feedback; Independency; 学習法; 音声; 自由度; ブラインド信号源分離; 畳み込み; 線形化; 反響音

In practical applications of BSS, processes of generating mixing and sensing signals include nonlinearity, caused by loud speakers, microphones, amplifiers and so on. BSS, cascading a signal group separation block and a linearization block has been proposed for low-order nonlinear mixtures. In the separation block, the signal sources are separated into each group, including its high-order components. The high-order components are further suppressed through the linearization block.In this report, separation performance of the nonlinear BSS is analyzed from several view points. The number of the sensors is increased from that of the signal sources in order to cancel the interference. Moreover, the interference components is decided by a ratio of the nonlinear and the linear components. A relation between the ratio of the components and the number of the sensors is analyzed. The number of the sensors can be reduced when the ratio of the nonlinearity is small. And a Cascade Form BSS Connecting Linearization and Source Separation and Linearization is analyzed.Next, effects of the initial guess of the separation matrix is analyzed. The training was carried out using 50 independent random initial guess, and good separation is obtained by a 25% probability. Moreover, effect of including 3rd-order terms is analyzed. When the 3rd-order term is under 10%, good separation performance can be obtained.

在盲分离的实际应用中，产生混合信号和感知信号的过程中会包含扬声器、麦克风、放大器等引起的非线性，针对低阶非线性混合信号，提出了级联信号组分离模块和线性化模块的盲分离方法。在分离块中，信号源被分离到每个组中，包括其高阶分量。通过线性化模块进一步抑制高阶分量。本文从多个角度分析了非线性盲分离系统的分离性能。传感器的数量从信号源的数量增加，以便消除干扰。此外，干扰分量由非线性分量和线性分量的比率决定。分析了传感器的组成比例与传感器数量的关系。当非线性的比率较小时，可以减少传感器的数量。然后分析了分离矩阵的初始估计对盲源分离的影响。使用50个独立的随机初始猜测进行训练，并且以25%的概率获得良好的分离。此外，包括三阶项的影响进行了分析。当三阶项小于10%时，可以获得较好的分离效果。

项目成果

K.Nakayama, A.Hirano, T.Sakai: "An adaptive nonlinear function controlled by estimated output pdf for blind source separation, pp.427-432, April 2003"Proc.4th International Symposium on Independent Component Analysis and Blind Source Separation (ICA2003),

K.Nakayama、A.Hirano、T.Sakai：“用于盲源分离的由估计输出 pdf 控制的自适应非线性函数，第 427-432 页，2003 年 4 月”Proc.4th 国际独立分量分析和盲源分离研讨会（

Effects of number of sensors in a BSS cascading group separation and linearization applied to nonlinear mixture

BSS 级联组分离和线性化中传感器数量的影响应用于非线性混合

• 发表时间: 2004
• 期刊: Proc. IFAC Workshop on Adaptation and Learning Control and Signal Precessing
• 作者: K.Nakayama;A.Hirano;T.Nishiwaki
• 通讯作者: T.Nishiwaki

Analysis of signal separation and distortion analysis in feedforward blind source separation for convolutive mixture

• DOI: 10.1109/mwscas.2004.1354328
• 发表时间: 2004-07
• 期刊: The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04.
• 作者: K. Nakayama;A. Hirano;Y. Dejima

A blind source separation cascading separation and linearization for low-order nonlinear mixtures

低阶非线性混合的盲源分离级联分离和线性化

• 发表时间: 2004
• 期刊: IEEE Proc. International Conference on Acoustics, Speech and Signal Processing
• 作者: T.Nishiwaki;K.Nakayama;A.Hirano
• 通讯作者: A.Hirano

K.Nakayama, A.Hirano, A.Horita: "A learning algorithm with adaptive exponential stepsize for blind source separation of convolutive mixtures with reverberations"IEEE&JNNS Proc.IJCNN'03, Portland, Oregon. (2003)

K.Nakayama、A.Hirano、A.Horita：“一种具有自适应指数步长的学习算法，用于带混响的卷积混合物的盲源分离”IEEE