基于稀疏性的相位谱补偿语音增强算法

相位谱补偿语音增强算法通过调整相位谱对噪声进行压缩,提高重构信号的质量。针对传统的相位谱补偿(phase spectrum compensation, PSC)语音增强算法采用固定的相位补偿因子,且算法的性能易受噪声估计准确性的影响,提出了一种基于稀疏性的相位谱补偿(sparsity-based phase spectrum compensation, SPSC)语音增强算法。首先,利用噪声估计算法得到噪声幅度谱,利用基于幅度谱的语音增强算法得到目标语音幅度谱;接着,通过噪声和目标语音幅度谱之间的局部信噪比(Signal-to-Noise Ratio, SNR)来估计谱时间稀疏性;然后,利用sigmoid函数改进相位补偿因子,联合补偿因子和谱时间稀疏性,得到SPSC函数。最后,使用SPSC函数对相位谱中的谱分量进行补偿,通过短时傅里叶逆变换得到最终增强后的语音信号。仿真实验表明,在四种不同背景噪声的低信噪比下,新的相位谱补偿算法使增强语音获得了更好的LSD、PESQ和segSNR指标,说明新的算法在低信噪比下,可以有效恢复带噪语音中的语音成分,对噪声抑制效果明显,增强语音的质量和听感均有一定提升。      

噪声环境下畸变模型线性化处理的顽健语音识别方法

针对噪声环境下语音识别的顽健性问题,考虑到梅尔倒谱系数(MFCC, Mel-frequency cepstral coefficient)域的畸变模型高度非线性且难以处理,用分段线性插值函数代替对数函数,提出了一种新的线性畸变模型.在此基础上,导出了噪声参数估计和声学模型补偿方法,无需采用矢量泰勒级数(VTS, vector Taylor series)展开作近似处理,有效避免了模型误差的引入,增强了系统在噪声环境下的顽健性.     

基于噪声整形的语音去噪算法

针对非平稳环境噪声提出一种基于噪声整形的语音去噪算法.该算法以最小感知均方误差为准则,在Wiener滤波的基础上,采用听觉感知加权函数修正Wiener滤波方程,实现对噪声谱整形,使噪声谱分布特性跟随语音谱而变:同时引入频率补偿因子克服非平稳噪声谱对语音影响的不均匀性;采用快速噪声估计算法实现对非平稳的估计.实验表明,该算法能更有效地抑制背景噪声,提高了去噪后的语音质量.     

基于GARCH模型的改进的倒谱域特征参数补偿算法

本文提出了一种改进的倒谱域特征参数补偿算法GMCSM。根据语音信号的时变特性,GMCSM算法使用广义自回归条件异方差(Generalized Auto-Regressive Conditional Heteroscedasticity,GARCH)模型对语音信号的方差进行建模。实验数据表明,与常规倒谱相减法CSM和MEMCSM相比,GMCSM能够更有效地补偿因加性噪声引起的倒谱特征参数失真,减少识别的错误率,特别是在信噪比较低的情况下,GMCSM的性能更为显著。     

一种用于抗噪语音识别的动态参数补偿新方法

模型补偿技术已成功应用到噪声环境下的语音识别任务中。流行的模型补偿技术如Log-Add和Log-Normal PMC（并行模型合并）方法对动态特征参数通常只能给出近似的补偿。因此他们的识别率在较低的信噪比条件下变得很低。本文利用静态特征的导函数推导出了一种新的动态模型参数补偿方法。新的方法可以同任何已知的静态模型补偿算法结合产生出新的用于识别的噪声语音模型。实验证明这一新算法的应用,使其识别率比仅使用原有的模型补偿算法有较为明显的提高,并且新算法的复杂度较原有的模型补偿算法只有轻微的增加。     

一种基于噪声估计的语音激活检测算法

针对当前语音激活检测算法在低信噪比和复杂噪声模型的环境下性能损失的问题,提出了一种基于噪声估计的语音激活检测算法,通过对背景噪声进行自适应估计,得到准确的信噪比门限,同时利用估计背景噪声对短时谱进行白化处理,从而使得谱熵判决准则得以适用于复杂噪声模型的环境。实验证明,算法在低信噪比和复杂噪声模型下性能优于G.729B和AMR中的语音激活检测算法。     

采用复高斯分布模型的两步噪声幅度谱估计算法

噪声幅度谱估计是有效抑制外界噪声干扰、提高语音增强算法整体输出性能的重要环节。但目前针对该问题的研究相对较少,常用的语音激活检测算法只能在语音不存在阶段对噪声信号的幅度谱进行更新或估计,无法适用于更为复杂的非平稳噪声环境。为克服这一问题,本文基于噪声频谱的复高斯分布模型假设,提出了新型的两步噪声幅度谱估计算法。算法首先采用软判决技术计算噪声信号的功率谱,然后再结合复高斯分布条件下信号幅度谱和功率谱之间的数学关系间接地获取噪声幅度谱的估计。文中基于这一结论给出了两种估计算法,并在多种噪声环境下对它们的性能进行了仿真评估,其测试结果有效表明了提出算法优良的估计性能。      

基于改进语音特征提取方法的语音识别

在分析语音特征提取方法基础上提出一种改进组合算法,并采用HMM声学模型和Viterbi算法进行模式训练和识别.实验结果表明,该算法在噪声环境中具有较好的鲁棒性,能有效提高噪声环境下中文连续语音识别的正确率,增强语音识别整体性能,因此在噪声环境下的语音识别系统中具有一定的实用价值.     

语音激活检测算法的设计与实现

深入研究了基于时域、频域、倒谱域和小波域特征参数的语音端点检测算法。根据语音的频域特性,提出了一种基于概率密度平方的改进谱熵法,增强了语音的谱线动态变化范围,改进了端点检测性能。为了满足抗多种噪声干扰的要求。提出了基于声道模型的算法和基于小波变换的算法。基于声道模型的算法利用了语音与噪声的声道差别,而基于小波变换的算法利用了语音的小波分解系数在不同频段具有的谐波特性。仿真结果表明这两种算法都具有良好的检测性能。     

抗噪声的小波谱压缩特征提取算法在语音识别中的应用

针对语音识别实际应用过程中的噪声问题,给出了一种新的抗噪声的特征提取算法,即先利用小波变换将语音信号进行小波子带分解,再根据人耳的听觉掩蔽效应,由谱压缩的技术,将小波变换后的子带语音信号进行压缩,从而提取其对应的语音特征。通过MATLAB软件建立实验平台,仿真实验结果表明该语音特征可以在噪声环境下得到较高的识别率。新的特征参数即充分利用了小波的抗噪声特性又有效地降低了语音识别中的训练环境和识别环境间的失配,具有抗噪声的特点。     

Feature Compensation Combining SNR‐Dependent Feature Reconstruction and Class Histogram Equalization

In this letter, we propose a new histogram equalization technique for feature compensation in speech recognition under noisy environments. The proposed approach combines a signal‐to‐noise‐ratio–dependent feature reconstruction method and the class histogram equalization technique to effectively reduce the acoustic mismatch present in noisy speech features. Experimental results from the Aurora 2 task confirm the superiority of the proposed approach for acoustic feature compensation.     

采用多级残差滤波的非局部均值图像去噪方法

为充分利用残差中的图像信息以提升非局部均值算法的去噪性能,该文提出一种多级残差图像滤波新方法。首先对含噪图像进行非局部均值滤波得到初始的去噪图像和权值分布矩阵,然后对残差图像进行固定权值非局部均值滤波来提取图像结构信息,将提取的信息经高斯平滑抑噪后作为补偿图像,与去噪图像相加得到增强的恢复图像。针对上述方法提出一种多级滤波的实现方案,从理论上推导证明了该方法的原理及可行性,并提出一种无需参考图像的迭代停止准则来自适应地优选滤波级数。实验结果表明,提出的迭代停止准则能够达到与峰值信噪比一致的优选结果;与经典的非局部均值算法相比,在计算效率相当的情况下,所提方法能够显著地提升其去噪性能,峰值信噪比平均可以提高1.2 dB,且具有更好的细节保持能力。     

基于Direct3D技术的VTS雷达PPI显示优化设计

针对VTS雷达一次回波的处理及显示问题,提出了优化坐标快速转换及回波数据实时显示处理的方案。该方案采用环形队列和二级缓存机制解决了实时接收数据丢包问题;并采用远区补偿方法结合Directx3D技术下的多图层融合解决了由坐标转换带来的图像缺损产生的摩尔纹,同时对回波显示进行了修正,且实现了多量程下的回波显示。该设计在节省系统资源的同时取得了更快的显示速度和更好的显示效果,并已在实际工程中得到了验证     

Individual-free representation-based classification for facial expression recognition

Facial expression recognition (FER) plays a significant role in human–computer interaction. However, in FER applications, the samples are usually corrupted by individual differences, which affect the classification result to some extent. This paper proposes an individual-free representation-based classification, which utilizes the variation training set (VTS) and the virtual variation training set (VVTS) to remit the side-effect caused by individual differences. The VTS and VVTS are both generated from the original training set and show possible variation of the expression. The new approach performs low-rank decomposition-based singular value decomposition for both VTS and VVTS, and then integrates them to determine the label of the query sample. This promising performance is mainly attributed to the fact that VTS and VVTS used in the proposed method can exploit limited original training set to produce a large possible expression variation. Experimental results show that the proposed method can achieve better performance than most of the competitive FER methods, e.g., SVM, SRC, CRC, LRC and the method in Lee et al.     

基于加权特征值补偿的说话人识别

背景噪声的存在,使得说话人识别系统的训练环境和测试环境发生失配,导致系统性能发生急剧下降。本论文提出一种加权特征值补偿算法,把由噪声引起的使带噪语音信号特征值与纯净语音特征值发生偏差的部分去除,从而使进入识别器的特征值接近纯净语音的特征值。在特征值补偿过程中引入了信噪比加权的方法。实验表明,这种方法能够有效的提高说话人识别系统的性能。     

一种提高语音干扰效果评估准确度的方法

语音信号的干扰效果是检验通信对抗装备的重要指标之一,基于客观的评估方法是当前研究的重点。客观评估方法的基础是对语音信号的预处理,介绍语音信号端点识别和语音信号分段处理方法的基础上,提出了一种基于时间统一设备的端点识别与分段方法,解决了加噪语音信号在仿真试验中的分段问题,该方法不受信噪比影响,具有较强的适应性。     

Noise-robust pitch detection method using wavelet transform with aliasing compensation

An improved wavelet-based method is developed for extracting pitch information from noisy speech. It uses a modified spatial correlation function which is originally applied to wavelet-based signal denoising to improve the performance of pitch detection in a noisy environment. The modified spatial correlation function needed in the proposed pitch detection method makes use of an aliasing compensation algorithm to eliminate the aliasing distortion that arises from the downsampling and upsampling operations of the wavelet transform. As a consequence, this allows one to further increase the accuracy of pitch detection. It is shown in various experimental results that this new method gives a considerable performance improvement when compared with other conventional and wavelet-based methods.     

Travelling wave expansion: a model fitting approach to the inverse problem of elasticity reconstruction

In this paper, a novel approach to the problem of elasticity reconstruction is introduced. In this approach, the solution of the wave equation is expanded as a sum of waves travelling in different directions sharing a common wave number. In particular, the solutions for the scalar and vector potentials which are related to the dilatational and shear components of the displacement respectively are expanded as sums of travelling waves. This solution is then used as a model and fitted to the measured displacements. The value of the shear wave number which yields the best fit is then used to find the elasticity at each spatial point. The main advantage of this method over direct inversion methods is that, instead of taking the derivatives of noisy measurement data, the derivatives are taken on the analytical model. This improves the results of the inversion. The dilatational and shear components of the displacement can also be computed as a byproduct of the method, without taking any derivatives. Experimental results show the effectiveness of this technique in magnetic resonance elastography. Comparisons are made with other state-of-the-art techniques.     

Graph regularized low-rank feature mapping for multi-label learning with application to image annotation

Automatic image annotation has emerged as a hot research topic in the last two decades due to its application in social images organization. Most studies treat image annotation as a typical multi-label classification problem, where the shortcoming of this approach lies in that in order to a learn reliable model for label prediction, it requires sufficient number of training images with accurate annotations. Being aware of this, we develop a novel graph regularized low-rank feature mapping for image annotation under semi-supervised multi-label learning framework. Specifically, the proposed method concatenate the prediction models for different tags into a matrix, and introduces the matrix trace norm to capture the correlations among different labels and control the model complexity. In addition, by using graph Laplacian regularization as a smooth operator, the proposed approach can explicitly take into account the local geometric structure on both labeled and unlabeled images. Moreover, considering the tags of labeled images tend to be missing or noisy, we introduce a supplementary ideal label matrix to automatically fill in the missing tags as well as correct noisy tags for given training images. Extensive experiments conducted on five different multi-label image datasets demonstrate the effectiveness of the proposed approach.