基于独立分量分析的低压电力线信号去噪

针对低压电力线中的噪声,提出了一种运用独立分量分析原理对低压电力线信号进行消噪的方法,详细研究了低压电力线信道噪声特性以及独立分量分析原理,应用基于负熵的FASTICA算法对低压电力线信道载波进行去噪,并与小波去噪的效果进行了比较。实验结果表明,该去噪方法的去噪效果与小波去噪效果接近,其特色是通过电力线信号与噪声信号的盲源分离实现噪声去除,与小波去噪方法相比,该方法更简单容易、去噪效果好、自适应能力强。     

基于核独立成分分析的声信号去噪方法

野外环境无线传感侦查网络中的声识别技术面临着复杂的自然环境噪声的挑战,尤其是由强风噪声造成的影响.独立成分分析(ICA)方法是一种能够较好地解决这种复杂环境去噪的方法.引入一种基于核方法的非线性ICA方法一核独立成分分析(KICA).基于该算法,针对强风噪声的特性,设计一种应用于单声传感器降噪的方案.通过降噪仿真实验,...     

基于UWT和独立分量分析的含噪盲源分离

提出了基于UWT（非抽样小波变换）去噪与FastICA（快速独立分量分析）算法相结合的含噪盲源分离方法,采用先去噪后分离的方式实现了在加性高斯噪声环境下混合图像的盲分离。仿真结果表明,该方法能很好地从加性高斯噪声中分离出源图像,与曲波阈值去噪后的FastICA方法相比较,该方法能获得更好的峰值信噪比。     

A new robust double-talk detector based on the Stockwell transform for acoustic echo cancellation

Despite great developments in the field of acoustic echo cancellation (AEC), the presence of double-talk remains difficult problem. The main role of double-talk detection (DTD) is to control adaptation of the filter coefficients by halting their update in double-talk situations. In this paper, we propose a new method of DTD based on a time–frequency analysis that uses the Stockwell transform (ST).The ST is a time–frequency spectral localization method that combines the characteristics of the short-time Fourier transform and the wavelet transform. This method provides better time–frequency resolution, especially for non-stationary signals. In the experimental tests, the normalized least mean squares (NLMS) algorithm is used to update the filter coefficients along with speech signals taken from the TIMIT database. The obtained results show better performance compared to existing methods in terms of misalignment convergence and speech intelligibility enhancement.     

基于盲源分离的超声信号去噪的仿真研究

提出一种新的基于盲源分离的超声信号去噪方法.为了验证去噪方法的有效性,应用此方法处理了仿真的超声信号,并与小波去噪的效果进行了比较.实验结果表明:该去噪方法能极大提高超声信号的信噪比,且其效果能与小波去噪方法相媲美,其特点是通过超声信号和噪声信号的盲源分离实现噪声消除.     

A novel sub-band adaptive filtering for acoustic echo cancellation based on empirical mode decomposition algorithm

Acoustic echo cancellation is one of the most severe requirements in hands-free telephone and teleconference communication. This paper proposes an Empirical Mode Decomposition (EMD)-based sub-band adaptive filtering structure, which applies the EMD-based algorithm dealing with the far-end speech signal and the microphone output to obtain two sets of intrinsic mode functions (IMFs). In addition, each IMF set is separated into different bands based on the power spectral density (PSD) of every IMF. Experiment signals were collected from a medium-size office room and simulations were taken under different conditions by three types of EMD-based algorithms. Results show that the proposed structure is able to model the transfer function of the unknown environment and track the change of the room much faster than the normalized adaptive filtering structure. The ensemble EMD (EEMD) algorithm and the noise-modulated EMD (NEMD) are proved to have better performance than the EMD algorithm in terms of echo return loss enhancement.     

Robust extended multidelay filter and double-talk detector for acoustic echo cancellation

We propose an integrated acoustic echo cancellation solution based on a novel class of efficient and robust adaptive algorithms in the frequency domain, the extended multidelay filter (EMDF). The approach is tailored to very long adaptive filters and highly auto-correlated input signals as they arise in wideband full-duplex audio applications. The EMDF algorithm allows an attractive tradeoff between the well-known multidelay filter and the recursive least-squares algorithm. It exhibits fast convergence, superior tracking capabilities of the signal statistics, and very low delay. The low computational complexity of the conventional frequency-domain adaptive algorithms can be maintained thanks to efficient fast realizations. We also show how this approach can be combined efficiently with a suitable double-talk detector (DTD). We consider a corresponding extension of a recently proposed DTD based on a normalized cross-correlation vector whose performance was shown to be superior compared to other DTDs based on the cross-correlation coefficient. Since the resulting DTD also has an EMDF structure it is easy to implement, and the fast realization also carries over to the DTD scheme. Moreover, as the robustness issue during double talk is particularly crucial for fast-converging algorithms, we apply the concept of robust statistics into our extended frequency-domain approach. Due to the robust generalization of the cost function leading to a so-called M-estimator, the algorithms become inherently less sensitive to outliers, i.e., short bursts that may be caused by inevitable detection failures of a DTD. The proposed structure is also well suited for an efficient generalization to the multichannel case.     

基于声回波抵消两路算法的改进更新逻辑

声回波抵消两路算法被广泛用来检测系统双向通话;基于声回波抵消两路算法,提出了一种改进的控制更新逻辑。此更新逻辑通过比较滤波器的回波返回损失(ERLE),判断是否对滤波器进行更新。此改进更新逻辑能正确检测系统双向通话,避免滤波器的错误更新,并提高两路算法的收敛速度,减小存储器资源和计算量。仿真结果证实了此更新逻辑的有效性。     

Packet based echo cancellation for VoIP networks

In today’s modern telephony network, VoIP is fast emerging as one of the main communication techniques. However, the performance and the quality of VoIP are affected by echo. Packet Based Echo Canceller (PBEC) is introduced, as a solution to cancel echo in the VoIP network. PBEC can replace the current echo cancellers, which are located in the Public Switched Telephony Network (PSTN) central switches. The operating principle of the PBEC is explained and its advantages are highlighted. The performance of the PBEC using different speech codecs is also studied. Using the PBEC, a maximum Echo Return Loss Enhancement (ERLE) of 37.39 dB has been achieved when used with the Pulse Code Modulation (PCM) based speech codec. From the simulation results, it can be seen that the performance of the Adaptive Differential Pulse Code Modulation (ADPCM) clearly matches the performance of the PCM based speech codec. The other major problem affecting the VoIP network is the issue of packet loss. This issue of packet loss has been successfully addressed in this paper by the insertion of random values. With the insertion of random values, the ERLE increases by 4.81 dB compared to when there is no insertion of random value. The PBEC with the utilization of random values would make the VoIP a better communication tool.     

Efficient source adaptivity in independent component analysis

A basic element in most independent component analysis (ICA) algorithms is the choice of a model for the score functions of the unknown sources. While this is usually based on approximations, for large data sets it is possible to achieve "source adaptivity" by directly estimating from the data the "true" score functions of the sources. We describe an efficient scheme for achieving this by extending the fast density estimation method of Silverman (1982). We show with a real and a synthetic experiment that our method can provide more accurate solutions than state-of-the-art methods when optimization is carried out in the vicinity of the global minimum of the contrast function.     

Estimating functions of independent component analysis for temporally correlated signals

This article studies a general theory of estimating functions of independent component analysis when the independent source signals are temporarily correlated. Estimating functions are used for deriving both batch and on-line learning algorithms, and they are applicable to blind cases where spatial and temporal probability structures of the sources are unknown. Most algorithms proposed so far can be analyzed in the framework of estimating functions. An admissible class of estimating functions is derived, and related efficient on-line learning algorithms are introduced. We analyze dynamical stability and statistical efficiency of these algorithms. Different from the independently and identically distributed case, the algorithms work even when only the second-order moments are used. The method of simultaneous diagonalization of cross-covariance matrices is also studied from the point of view of estimating functions.     

Performance analysis of under-modelling stereophonic acoustic echo cancellation by adaptive filtering LMS algorithm

This paper addresses the field of stereophonic acoustic echo cancellation (SAEC) with adaptive filtering algorithms. In SAEC applications, using the least mean square (LMS) algorithm, it is usually assumed that the lengths of the adaptive filters are equal to that of the unidentified system responses. Although, in many realistic situations, under-modelled lengths adaptive filters, whose lengths are less than that of the unidentified systems (under-modelled systems), are employed, and analysis results for the exact modelled stereophonic LMS algorithm are not automatically appropriate to the under-modeled lengths. In this paper, we present a statistical analysis of the under-modeled stereophonic LMS algorithm. Exact expressions and deterministic recursive equations to the mean coefficients behavior of the adaptive LMS filters are derived to completely characterize and assess the performances (transient and steady-state) of the under-modeling stereophonic LMS algorithm. The expected theoretical behaviour is compared with Monte Carlo simulations and practical experimental results, showing a very good agreement.     

Improved variable step-size NLMS adaptive filtering algorithm for acoustic echo cancellation

Acoustic echo canceller (AEC) is used in communication and teleconferencing systems to reduce undesirable echoes resulting from the coupling between the loudspeaker and the microphone. In this paper, we propose an improved variable step-size normalized least mean square (VSS-NLMS) algorithm for acoustic echo cancellation applications based on adaptive filtering. The steady-state error of the NLMS algorithm with a fixed step-size (FSS-NLMS) is very large for a non-stationary input. Variable step-size (VSS) algorithms can be used to decrease this error. The proposed algorithm, named MESVSS-NLMS (mean error sigmoid VSS-NLMS), combines the generalized sigmoid variable step-size NLMS (GSVSS-NLMS) with the ratio of the estimation error to the mean history of the estimation error values. It is shown from single-talk and double-talk scenarios using speech signals from TIMIT database that the proposed algorithm achieves a better performance, more than 3 dB of attenuation in the misalignment evaluation compared to GSVSS-NLMS, non-parametric VSS-NLMS (NPVSS-NLMS) and standard NLMS algorithms for a non-stationary input in noisy environments.     

具有双方对讲保护的自适应回波消除新算法

基于电话会议的声学回波中的双方对讲情况,本文提出了一个无需设置双方对讲检测器,但仍能在双讲过程中保护自适应滤波器消除性能的NLMS类算法.由于可以由远端信号和近端混合接收信号之间的相关性系数的变化来判断双讲发生或回波路径改变,所以改进的算法中直接将其代入滤波器权系数的迭代公式中,从而控制滤波器系数更新的快慢.仿真结果表明与同类算法相比,采用更小的计算量,该算法在双方对讲时能较好地起到保护作用,而在回波路径改变时也具有快速的跟踪性能.     

基于独立成分分析的反卷积新方法

基于独立成分分析方法进行了反卷积研究。独立成分分析算法中要求混合的观测信号不少于从这些观测信号中分离出的独立成分数。针对反卷积中混合的观测信号路数不满足上述条件的问题,提出了一种新的基于独立成分分析的反卷积方法,该方法通过对输入信号进行变换构造出新的观测信号,并对卷积模型进行非线性变换,采用独立成分分析算法实现解卷积混叠。仿真实验结果表明,该方法具有较好的性能,并能实现对信道瞬态响应信号的提取。     

基于盲信号分离的回波抵消技术

针对数字直放站回波抵消技术中自适应滤波法在多径回波信道条件下不能完全消除次径回波的问题,提出了基于盲信号分离的直放站回波抵消方法。首先对施主天线接收的混合信号进行相空间重构,使观测信号的数目大于等于独立信源的数目;然后利用独立分量分析法（ICA）对重构的信号进行盲信号分离;最后根据各分离信号和发送信号的相关情况判断有用信号,实现回波消除。对复杂多径回波信道条件下的多载波全球移动通信系统（GSM）信源进行回波抵消测试,分离得到的有用信号的相关系数可以达到0.9593。表明盲信号分离的方法可以实现复杂多径信道下的直放站回波抵消,有效解决了传统的自适应滤波法存在的问题。     

基于归一化互相关法的声学回声消除及仿真

全双工免提通信系统中,要获得好的声学回声消除效果,提高语音质量,关键要解决双端发声问题,双端发声检测的准确性直接影响声学回声消除效果。由于基于能量和基于互相关双端发声检测算法存在门限值设置难,以及检测统计量对回声信道变化敏感的问题。对归一化互相关法进行了研究,得出此算法理论上不存在以上问题,通过采集真实语音信号,计算机仿真,从实验证明了此方法确实可行,并具有非常好的声学回声消除效果。     

一种信号适度失真的宽线性SAEC模型

现有的立体声回声抵消器是一个实变量双输入双输出的装置,其结构复杂不易实现。宽线性模型的引入,提供了一种复变量单输入单输出的装置来替代实变量双输入双输出装置,其优点是只需处理一个复变量的输出信号而不是两个实变量输出信号,而且能通过复变量输入信号的相位和幅值分别调控声音的立体感和音质。利用输入信号适度失真的方法降低两个信号之间的相关性以解决因滤波而产生的非唯一性问题。把宽线性模型和失真信号应用到仿射投影算法中,通过仿真验证改进方法的误差性能和收敛速度。结果表明改进的方法具有误差小和收敛快的特点,因此宽线性SAEC模型更有优势。     

基于小波分解的独立分量掌纹识别方法

独立分量分析方法在图像处理中具有独特的优势，用于掌纹特征提取，使得变换后的各分量之间不仅互不相关，而且还尽可能的统计独立，能更全面的揭示掌纹特征间的本质结构。为了降低运算复杂度，提出了一种基于小波分解的独立分量掌纹特征提取方法。首先对掌纹图像做小波变换进行降维，在保留原始图像轮廓信息和细节信息的基础上，去掉高频噪声，然后进行独立分量分析，采用FastICA算法，试验结果表明,本方法比传统的独立分量分析方法的识别率更高，且计算量大大减少。