基于影响因子的频域盲源分离排序算法

卷积混合信号盲源分离可以在频域得到有效解决,但频域盲源分离必须解决排序问题.本文研究了频点距离和各频点分离质量对基于相邻频点幅度相关性的排序算法的影响,提出了改进的频域盲源分离排序算法.改进算法通过影响因子来控制频点距离和各频点分离质量对排序的影响,距离小且分离质量好的频点设置较大影响因子,距离大或分离质量不好的频点则设置较小影响因子.文中详细讨论了影响因子的设定函数.最后对瞬时混合信号、卷积混合信号、实际房间采集信号分别进行盲源分离实验.实验结果表明了本文算法的有效性.     

基于相邻频点幅度相关的语音信号盲源分离

排序和幅度不一致性是在频域进行信号盲源分离的主要困难。针对语音信号邻近频点间信号幅度相关性能良好这一特点，本文提出基于相邻频点间幅度相天的盲源分离算法，用以消除卷积信号盲源分离过程中排序不确定性。本算法理论简单，稳健性好。仿真结果表明该方法对卷积混合后的语音信号能得到较好的分离效果，并且耗时较短。     

基于区域增长校正的频域盲源分离排序算法

卷积盲源分离可以在频域得到有效解决,但频域盲源分离必须解决排序模糊问题。该文提出一种基于区域增长校正的频域盲源分离排序算法。首先对卷积混合信号短时傅里叶变换,在频域的各个频点处建立瞬时模型进行独立分量分析,在此基础上使用分离信号功率比的相关性,对所有频点进行逐点排序置换。其次根据阈值将排序后的结果划分为若干个小区域。最后按区域增长方式进行区域置换与合并,最终得到正确的分离信号。区域增长校正可最大限度地减少频点排序错误扩散现象,从而改善分离效果。在模拟和真实环境中分别进行语音盲源分离实验,结果表明所提算法的有效性。     

宽带恒定束宽盲波束形成算法

针对传统盲源分离算法对宽带阵列信号适用性较差的问题,提出一种基于时频分析的宽带恒定束宽盲波束形成算法。该算法首先将接收信号变换到时频域上并提取出单源点。然后,对单源点聚类并求解信号在不同频点上的导向矢量。最后,通过提出一种信号来向未知的空间响应变化约束方法,实现宽带恒定束宽盲波束形成。该算法避免了将宽带盲波束形成转换为卷积混合的盲源分离,因而不存在时域盲源分离算法中系统参数随滤波器阶数急剧增加的问题,也不存在频域算法中排序和幅度模糊的问题。仿真结果表明,算法能够较好地实现宽带信号的盲分离,且输出信干噪比高于时域、频域以及时频域盲源分离算法,实测数据的处理结果验证了该算法的实用性。      

基于单个频点的水声信号盲源分离

该文提出基于单个频点的卷积信号盲源分离方法,利用该方法不但可以有效克服频域盲分离过程中排序不确定问题,而且在分离过程中,无需考虑幅度不一致问题。将该方法用于水声信号的盲分离,仿真结果表明基于单个频点盲源分离方法能够很好地分离水声卷积混合信号。与基于两个频点盲源分离方法相比较,其分离效果更优,并且能有效节省CPU运算时间,因而更适合于对信号进行实时处理。     

基于邻近频点相关特性的水声信号盲源分离

排序和幅度不一致性是信号频域盲源分离的主要困难。该文建立了邻近频点相关特性理论,并针对水声信号进行深入研究,结论表明单个水声信号邻近频点间相关特性良好,且性能非常稳定;而两个不同水声信号邻近频点相关性非常弱。提出基于邻近频点相关特性的盲源分离算法,用于消除卷积信号盲源分离过程中排序不确定性,实验表明该方法对卷积混合形式的水声信号能取得较好分离效果。     

功率比相关子带划分快速独立向量分析

传统独立向量分析利用频点之间的高阶相关性解决盲源分离频域排序问题,已有研究表明,频点之间的高阶相关性与频点间距有关,越近的频点相关性越强。考虑此特点,本文提出在频域进行无重叠子带划分,采用功率比相关的方法解决子带之间的排序问题;结合更符合语音分布模型的多变量广义高斯分布和多变量t分布,实现了性能更优的功率比相关子带划分快速独立向量分析算法。实验结果表明,本文提出的算法相比传统独立向量分析算法具有更好的语音分离性能。      

一种有效的语音信号盲分离方法

频域盲语音信号分离存在着排序模糊问题,提出一种基于相邻频点幅度相关和DOA估计相结合的解排序模糊方法,并且通过对一系列预处理（白化）、独立分量分析和后处理算法的优化和有机组合,很好地实现了卷积混合语音信号的盲分离。用真实录制的语音信号进行了仿真实验,恢复出来的源信号的信干比较分离之前提高了约13dB,证明了算法的有效性。     

一种频域盲分离算法在语音分离中的应用

频域分离算法将时域计算复杂的解卷积问题变换为频域简单的瞬时分离问题。采用基于自然梯度的迭代函数实现瞬时盲分离,在频域用瞬时盲分离解决时域卷积盲分离问题时,遇到的两个难点就是频点间幅度和排列次序不确定性,为此我们分别采用归一化方法和分阶段分离方法来解决上述两个问题,仿真实验证明了算法的有效性。     

一种新的频域盲语音分离排序算法

针对频域盲源分离过程中存在的排序模糊性问题,提出了一种新的解决方法.该方法将整个频段分为低频、中频和高频三个部分.在低频段采用比较不同频率点间幅度相关系数大小的排序算法,在中频段采用基于波束形成方位估计的排序算法,在高频段采用比较幅度相关系数大小和波束形成相结合的排序方法.实验中采用评价盲分离算法性能的工具箱BSS_EVAL作为评价标准,仿真结果表明,该排序算法的分离性能大大优于单独采用比较幅度相关系数大小的排序算法和单独基于波束形成方位估计的排序算法.     

基于相关矩阵的频域盲分离排序方法

排列模糊性和幅度模糊性一直是在频域上分离卷积混合信号所面临的主要问题,针对该问题,给出了一种基于相邻频点的幅度相关之和的、快速有效地解决频域分离算法中排列模糊性的方法;即通过定义相邻频点的相关矩阵并通过其置换形式来解决排列模糊问题,从而在频域上有效的分离源信号,仿真证明,该算法可以对卷积混合信号实行快速有效分离,分离效果理想,并大幅减少计算量。     

结合ICA和复数神经网络的二麦阵列盲源分离技术

为了降低语音信号盲源分离算法的延时,提高其准确性和稳定性,本文结合传统盲源分离技术和深度神经网络的优势,提出了一种基于ICA独立分量分析和复数神经网络的二麦阵列盲源分离技术。本文将复数递归神经网络和独立分量分析方法有机融合,提出一种基于时频域的双通道复数神经网络,同时解决了独立分量分析中的排列问题。所提方法利输入混合信号利用复数域神经网络计算初始化分离矩阵,神经网络输出采用复数域形式,利用复数学习标签估计复数矩阵,然后采用独立分量分析方法获得目标分离矩阵。实验数据表明,所提方法相较于其它独立分量分析方法提高了盲源分离的实时性和准确性。      

基于欠定盲源分离的同步跳频信号网台分选

针对同步跳频(FH)网台分选问题,该文提出一种基于时频域单源点检测的欠定盲源分离(UBSS)分选算法.该算法首先对观测信号时频变换,利用自适应阈值去噪算法消除时频矩阵背景噪声,增加算法抗噪性能,然后根据信号绝对方位差算法进行单源点检测,有效保证单源点的充分稀疏性,并通过改进的模糊值聚类算法完成混合矩阵和2维波达方向估计...     

Wideband Blind Source Separation Algorithm Based on Beamforming

As the problem of array mixing model of wideband signals cannot be solved by conventional blind source separation algorithms, an improved algorithm based on beamforming is proposed in this paper. First, the received signals are transformed into time–frequency domain, and the delays of source signals are estimated. Then, the received signals are compensated with the estimated delay in frequency domain. Finally, the desired signal is acquired by using Frost wideband beamforming algorithm. Due to adopting the new methods of single source point extraction and delay estimation, the complexity of the proposed algorithm is reduced. Pre-steering delay is used in frequency domain to eliminate the compensation error when the delay is not an integer multiple of the sampling interval, which improves the separation performance significantly. The simulation results show that the proposed algorithm can adequately solve the problem of delay mismatch and achieve wideband blind source separation effectively. The existing algorithms are mostly fail for frequency hopping signals when there are numerous overlapping time–frequency points. In this case, the proposed algorithm still has good separation performance.

     

Blind identification of MIMO FIR systems driven by quasistationary sources using second-order statistics: a frequency domain approach

This paper discusses a frequency domain method for blind identification of multiple-input multiple-output (MIMO) convolutive channels driven by white quasistationary sources. The sources can assume arbitrary probability distributions, and in some cases, they can even be all Gaussian distributed. We also show that under slightly more restrictive assumptions, the algorithm can be applied to the case when the sources are colored, nonstationary signals. We demonstrate that by using the second-order statistics of the channel outputs, under mild conditions on the nonstationarity of sources, and under the condition that channel is column-wise coprime, the impulse response of the MIMO channel can be identified up to an inherent scaling and permutation ambiguity. We prove that by using the new algorithm, under the stated assumptions, a uniform permutation across all frequency bins is guaranteed, and the inherent frequency-dependent scaling ambiguities can be resolved. Hence, no post processing is required, as is the case with previous frequency domain algorithms. We further present an efficient, two-step frequency domain algorithm for identifying the channel. Numerical simulations are presented to demonstrate the performance of the new algorithm.     

A Novel and Fast Algorithm for Solving Permutation in Convolutive BSS,Based on Real and Imaginary Decomposition

In this paper, a new fast method for solving the permutation problem in convolutive BSS is presented. Typically, by transferring signals to the frequency domain, the convolutive BSS problem is converted to an instantaneous BSS, and deconvolution takes place in each frequency bin. However, another major problem arises which is permutation ambiguity in the frequency domain. Solving the permutation ambiguity for N sources in frequency domain needs N! comparisons between adjacent frequency bins. This drastically increases the overall computational complexity of the convolutive BSS. In our new approach, the complex-valued signals are decomposed into real and imaginary parts in each frequency bin. We show that the ideal mixing matrix has to possess a simple and symmetric structure. Accordingly, the structure can be exploited for solving the permutation ambiguity in frequency domain. Although separation in subband is accomplished by the FastICA algorithm, the proposed method requires modification of the separation algorithm, and a new structure is imposed on the mixing matrix. After that signals are separated by means of the FastICA, the permutation correction takes place only by N comparisons, decreasing the computational complexity. Comparing to five competitive methods, we experimentally demonstrate that permutation ambiguity is resolved accurately by this very fast approach while substantially decreasing the order of calculations. In terms of the separation performance and signal quality, the proposed method is superior to four of the compared methods and almost similar to the best of them.