Nonlinear cepstral equalisation method for noisy speech recognition

The authors deal with the problem of automatic speech recognition in the presence of additive white noise. The effect of noise is modelled as an additive term to the power spectrum of the original clean speech. The cepstral coefficients of the noisy speech are then derived from this model. The reference cepstral vectors trained from clean speech are adapted to their appropriate noisy version to best fit the testing speech cepstral vector. The LPC coefficients, LPC derived cepstral coefficients, and the distance between test and reference, are all regarded as functions of the noise ratio (the spectral power ratio of noise to noisy speech). A gradient based algorithm is proposed to find the optimal noise ratio as well as the minimum distance between the test cepstral vector and the noise adapted reference. A recursive algorithm based on Levinson-Durbin recursion is proposed to simultaneously calculate the LPC coefficients and the derivatives of the LPC coefficients with respect to the noise ratio. The stability of the proposed adaptation algorithm is also addressed. Experiments on multispeaker (50 males and 50 females) isolated Mandarin digits recognition demonstrate remarkable performance improvements over noncompensated method under noisy environment. The results are also compared to the projection based approach, and experiments show that the proposed method is superior to the projection approach under a severe noisy environment     

Cepstral behaviour due to additive noise and a compensation schemefor noisy speech recognition

The speech cepstral coefficients affected by additive noise are investigated. The cepstral vector changes as the level of additive noise increases. The behaviour of cepstral vector change shows that the cepstral vector shrinks in its norm and converges to the cepstral vector of the noise. This nonlinear behaviour of the cepstral vector can be approximated by a simple linear expression. Based on this representation, a model adaptation method is developed using deviation vectors. For every model state mean, a deviation vector is calculated according to the extracted noise spectrum and a pre-defined noise-to-signal ratio. During the pattern matching, an optimal scaling factor for the deviation vector is determined frame by frame, and the scaled deviation vector is added to the state mean of speech models so that the clean speech models are adapted to the noisy environment. Experimental results show that the proposed method is effective for white noise and coloured noise. It also outperforms the weighted projection measure method in experiments     

基于超高斯激励的噪声顽健语音线性预测分析算法

针对传统的语音信号线性预测分析算法在噪声环境下性能恶化的问题,提出了一种新的基于超高斯激励的噪声顽健线性预测算法。该算法采用具有超高斯特性的学生t分布对语音信号线性预测激励建模,并显式地考虑环境噪声的影响,从而构建语音信号线性预测分析的概率图模型。在此基础上,利用变分贝叶斯的方法求解模型参数的近似后验分布,进而实现对带噪语音线性预测系数的最优估计。实验结果表明,该算法能够有效提高噪声环境下语音信号线性预测分析的顽健性。     

Phase regression approach for estimating the parameters of a noisy multifrequency signal

A novel approach for estimating the parameters of a multifrequency signal from discrete samples corrupted by additive noise is presented. An established mathematical model indicates that noise influence on the discrete phase and amplitude spectra is equivalent to additive phase and amplitude noise, respectively. On this basis, a simple algorithm is proposed to estimate the frequency and phase of each sinusoid component by linear regression on the phase spectra of segmented signal blocks, while an amplitude estimator is directly derived from the spectrum of the window function. The circular nature of the phase spectrum is thoroughly explored. Also, an algorithmic scheme is presented. The derived variances of the estimators show that for a noisy signal this approach provides superior accuracy over the traditional approaches. Simulations and engineering application confirm the validity of the presented method.     

车载自组织网络中基于椭圆曲线零知识证明的匿名安全认证机制

依据车载自组织网络的特点,提出了一种基于椭圆曲线零知识证明的匿名安全认证机制,利用双向匿名认证算法避免消息收发双方交换签名证书,防止节点身份隐私在非安全信道上泄露;利用基于消息认证码的消息聚合算法,通过路边单元协助对消息进行批量认证,提高消息认证速度,避免高交通密度情形下大量消息因得不到及时认证而丢失。分析与仿真实验表明,该机制能实现车辆节点的隐私保护和可追踪性,确保消息的完整性。与已有车载网络匿名安全认证算法相比,该机制具有较小的消息延迟和消息丢失率,且通信开销较低。     

Fast identification of autoregressive signals from noisy observations

The purpose of this brief is to derive, from the previously developed least-squares (LS) based method, a faster convergent approach to identification of noisy autoregressive (AR) stochastic signals. The feature of the new algorithm is that in its bias correction procedure, it makes use of more autocovariance samples to estimate the variance of the additive corrupting noise which determines the noise-induced bias in the LS estimates of the AR parameters. Since more accurate estimates of this corrupting noise variance can be attained at earlier stages of the iterative process, the proposed algorithm can achieve a faster rate of convergence. Simulation results are included that illustrate the good performances of the proposed algorithm.     

Cepstrum third-order normalisation method for noisy speechrecognition

A new cepstrum normalisation method is proposed which can be used to compensate for distortion caused by additive noise. Conventional methods only compensate for the deviation of the cepstral mean and/or variance. However, deviations of higher order moments also exist in noisy speech signals. The proposed method normalises the cepstrum up to its third-order moment, providing closer probability density functions between clean and noisy cepstra than is possible using conventional methods. From the speaker-independent isolated-word recognition experiments, it is shown that the proposed method gives improved performance compared with that of conventional methods, especially in heavy noise environments     

The Cramer-Rao lower bound for bilinear systems

Estimation of the unknown parameters that characterize a bilinear system is of primary importance in many applications. The Cramer-Rao lower bound (CRLB) provides a lower bound on the covariance matrix of any unbiased estimator of unknown parameters. It is widely applied to investigate the limit of the accuracy with which parameters can be estimated from noisy data. Here it is shown that the CRLB for a data set generated by a bilinear system with additive Gaussian measurement noise can be expressed explicitly in terms of the outputs of its derivative system which is also bilinear. A connection between the nonsingularity of the Fisher information matrix and the local identifiability of the unknown parameters is exploited to derive local identifiability conditions of bilinear systems using the concept of the derivative system. It is shown that for bilinear systems with piecewise constant inputs, the CRLB for uniformly sampled data can be efficiently computed through solving a Lyapunov equation. In addition, a novel method is proposed to derive the asymptotic CRLB when the number of acquired data samples approaches infinity. These theoretical results are illustrated through the simulation of surface plasmon resonance experiments for the determination of the kinetic parameters of protein-protein interactions.     

在小波域中进行图像噪声方差估计的EM方法

提出一种估计图像噪声的方法,该方法用混合高斯概率密度模型拟合图像的小波系数中最高频率子带的直方图,用EM算法估计模型的参数,选取其中最小的标准方差作为图像噪声标准方差。用该方法能准确地估计图像高斯噪声的标准方差,尤其当图像的噪声比较弱时,该方法比传统方法更准确。     

Generalized Robust Multichannel Frequency‐Domain LMS Algorithms for Blind Channel Identification

Recently, several noise‐robust adaptive multichannel LMS algorithms have been proposed based on the spectral flatness of the estimated channel coefficients in the presence of additive noise. In this work, we propose a general form for the algorithms that integrates the existing algorithms into a common framework. Computer simulation results are presented and demonstrate that a new proposed algorithm gives better performance compared to existing algorithms in noisy environments.     

基于时频阈值的小波包语音增强算法

该文考虑小波域应用语音降噪中听觉掩蔽效应,提出了一种基于时频阈值的小波包语音增强算法。新算法首先通过频域增强方法得到语音粗估计,通过跟踪估计语音时频特性的细节变化,及时调节降噪阈值,然后利用时频阈值对小波包系数进行处理,以达到语音降噪的目的。实验表明,较传统小波域语音降噪方法,新算法在抑制平稳白噪声的同时减小了语音信息的损失,其增强语音的MOS(Mean Opinion Score)评分、输出信噪比、MBSD(Modified Bark Spectral Distortion)测度性能均有明显提高。     

基于MPEG-AAC编码器的压缩域音频增强方法

本文基于MPEG-AAC音频编解码器,提出了一种压缩域的音频增强方法.首先,对含噪音频信号的比特流进行解码,得到含噪音频信号的MDCT系数;然后,利用修正的加权递归平均（Modified Weighted Recursive Averaging,MWRA）方法估计噪声功率;再者,利用基于听觉掩蔽原理的自适应β-阶双曲余弦（COSH）统计模型,对含噪音频的MDCT系数进行增强处理;最后,将增强后的MDCT系数重新量化编码,得到用于解码的增强比特流实验结果表明,本文提出的方法能有效去除AAC解码音频信号中的多种背景噪声,其性能明显优于参考方法.     

基于分数阶谱相减的语音增强法

该文提出了基于分数阶谱相减的语音增强法(FSS)。该方法通过对带噪语音信号作分数阶傅里叶变换(FRFT),将得到的分数阶语噪混合谱与估计的分数阶噪声谱相减,最后利用分数阶Fourier反变换获得去噪后的语音信号。理论分析表明,所提方法存在一个最佳分数阶阶数,使得语噪混合信号能在分数阶变换域得到最好的分离,从而有效地提高了增强语音的性能。计算机仿真表明,对于混有加性白噪声的男/女声发音信号,所提方法在信噪比提高量和Itakura距离减少量两个方面都优于传统的谱相减法(SS),并且增强语音中的音乐噪声得到了明显抑制。     

基于Teager能量算子的自适应小波语音增强

小波阈值的自适应计算方法有多种形式,基于Teager能量算子(TEO)的是其中一种.将这种方法结合离散小波分解使用时,会对实际噪声产生过多的保留.根据色噪声的具体特征,对这种方法进行了改进,对染噪信号的高频频带和低频频带分别使用不同的方法进行处理,这种处理既能有效保护清音,又能去除噪声.仿真处理结果表明,这种改进能更好地解决语音信号的保护和噪声消除之间的矛盾.     

Higher order statistics based IIR notch filtering scheme forenhancing sinusoids in coloured noise

It is known that sinusoids generate lines in their spectra, but false lines may appear when the sinusoids are corrupted by coloured additive noise. In the paper, a higher-order statistics-based IIR filtering scheme is suggested to suppress additive coloured noise, thus enhancing the desired spectral peaks due to the sinusoids. The filter used is an unknown pole-zero constrained IIR notch filter. The filter coefficients are estimated by applying the linear prediction (LP) method to a block of a fourth-order mixed cumulant slice (FOMCS) of the input noisy signal. Therefore, the presented scheme automatically handles Gaussian noise (white or coloured). In the non-Gaussian noise case, a novel analysis is presented to show that, associated with the FOMCS, there is a new signal-to-noise ratio called the `signal-to-noise kurtosis ratio' (SNKR). This SNKR is a multiple of the conventional SNR if the additive noise is coloured non-Gaussian. Thus, the presented scheme is capable of handling additive coloured noise (Gaussian or non-Gaussian). The performance of the proposed scheme, compared with a correlation-based counterpart, is demonstrated through computer simulations     

Filtering of Filter‐Bank Energies for Robust Speech Recognition

We propose a novel feature processing technique which can provide a cepstral liftering effect in the log‐spectral domain. Cepstral liftering aims at the equalization of variance of cepstral coefficients for the distance‐based speech recognizer, and as a result, provides the robustness for additive noise and speaker variability. However, in the popular hidden Markov model based framework, cepstral liftering has no effect in recognition performance. We derive a filtering method in log‐spectral domain corresponding to the cepstral liftering. The proposed method performs a high‐pass filtering based on the decorrelation of filter‐bank energies. We show that in noisy speech recognition, the proposed method reduces the error rate by 52.7% to conventional feature.     

基于降码率设计的图像编码处理技术研究

为了降低老化的图像采集设备引入的加性噪声所带来的图像数据冗余,研究了加性噪声对图像和视频的影响,提出用三维块匹配(Block Matching 3D,BM3D)算法处理受噪的静态图像,验证了通过降噪来降低图像信息熵和数据量的方法,进而提出降噪--编码方案。首先采用四维视频块匹配(Video Block Matching 4D,VBM4D)算法对受噪视频进行降噪处理,随后进行H.264编码。经过此方案处理的图像信息熵降低16%,数据量减少38%;在视频质量未显著降低的前提下,编码码流减少59.5%。数据表明该方法能在保证视频质量的前提下显著提升H.264的编码压缩率,促进视频在小带宽通信系统中的传输。与H.264以及神经网络等编码方案相比,该方案复杂度低,能相对实时地处理视频。     

A new extraction method for noise sources and correlationcoefficient in MESFET

A new extraction method for noise sources and correlation coefficient in the noise equivalent circuit of GaAs metal semiconductor field effect transistor (MESFET) is proposed. It is based on the linear regression, which allows us to extract physically meaningful parameters from the measurement in a systematic and straightforward way. The confidence level of the measured data can also be easily examined from the linearity, y-intercept of the linear regression, and the scattering from the regression line. Furthermore, it is found that the time constant of correlation coefficient whose value is almost the same as that of the transconductance should be considered to model noise parameters accurately. The calculated values of minimum noise figure, optimum impedance, and noise resistance using above approach, show excellent agreement with measurement for a typical MESFET device studied in this paper     

Reconstruction of polynomial systems from noisy time-seriesmeasurements using genetic programming

The problem of functional reconstruction of a polynomial system from its noisy time-series measurement is addressed in this paper. The reconstruction requires the determination of the embedding dimension and the unknown polynomial structure. The authors propose the use of genetic programming (GP) to find the exact functional form and embedding dimension of an unknown polynomial system from its time-series measurement. Using functional operators of addition, multiplication and time delay, they use GP to reconstruct the exact polynomial system and its embedding dimension. The proposed GP approach uses an improved least-squares (ILS) method to determine the parameters of a polynomial system. The ILS method is based on the orthogonal Euclidean distance to obtain an accurate parameter estimate when the series is corrupted by measurement noise. Simulations show that the proposed ILS-GP method can successfully reconstruct a polynomial system from its noisy time-series measurements     

A Novel Technique for the Identification of ARMA Systems Under Very Low Levels of SNR

In this paper, a novel technique for the identification of minimum-phase autoregressive moving average (ARMA) systems from the output observations in the presence of heavy noise is presented. First, starting from the conventional correlation estimator, a simple and accurate ARMA correlation (ARMAC) model in terms of the poles of the ARMA system is presented in a unified manner for white noise and impulse-train excitations. The AR parameters of the ARMA system are then obtained from the noisy observations by developing and using a residue-based least-squares correlation-fitting optimization technique that employs the proposed ARMAC model. As for the estimation of the MA parameters, it is preceded by the application of a new technique intended to reduce the noise present in the residual signal that is obtained by filtering the noisy ARMA signal via the estimated AR parameters. A scheme is then devised whereby the task of MA parameter estimation is transformed into a problem of correlation-fitting of the inverse autocorrelation function corresponding to the noise-compensated residual signal. In order to demonstrate the effectiveness of the proposed method, extensive simulations are performed by considering synthetic ARMA systems of different orders in the presence of additive white noise and the results are compared with those of some of the existing methods. It is shown that the proposed method is capable of estimating the ARMA parameters accurately and consistently with guaranteed stability for signal-to-noise ratio (SNR) levels as low as $-{5}~{hbox {dB}}$ . Simulation results are also provided for the identification of a human vocal-tract system using natural speech signals showing a superior performance of the proposed technique in terms of the power spectral density of the synthesized speech signal.