基于非平滑非负矩阵分解语音增强

针对非负矩阵分解稀疏性不够,通过引入平滑矩阵调节字典矩阵和系数矩阵的稀疏性,提出基于非平滑非负矩阵分解语音增强算法。算法通过语音和噪声的先验字典学习构造联合字典矩阵;然后通过非平滑非负矩阵分解更新带噪语音在联合字典矩阵下的投影系数实现语音增强;同时通过滑动窗口法实时更新先验噪声字典。仿真结果表明,该算法相对非负矩阵分解语音增强算法和MMSE算法具有更好的抑制噪声能力。     

稀疏卷积非负矩阵分解的语音增强算法

非平稳噪声和低信噪比条件下提高增强语音质量一直以来都是语音增强研究的难题。近年来,卷积非负矩阵分解在语音增强算法中成功应用,本文进一步考虑语音信号在时频域的稀疏性,提出了稀疏卷积非负矩阵分解(Sparse Convolutive Nonnegative Matrix Factorization, SCNMF)的语音增强算法。该算法包括训练和增强两个阶段。训练阶段通过SCNMF算法分别对纯净语音和噪声的频谱进行训练,得到纯净语音和噪声字典,并将其作为增强阶段的先验信息。增强阶段首先通过SCNMF算法对带噪语音的频谱进行分解,然后利用纯净语音和噪声联合字典对语音编码矩阵进行估计,重构增强语音。本文通过实验仿真分析了稀疏因子对增强语音质量的影响。实验结果表明,在非平稳噪声和低信噪比条件下,本文算法增强效果均优于多带谱减、非负矩阵分解、卷积非负矩阵分解等传统的算法。     

稀疏正则非负矩阵分解的语音增强算法

对于非负矩阵分解的语音增强算法在不同环境噪声的鲁棒性问题,提出一种稀疏正则非负矩阵分解（SRNMF）的语音增强算法。该算法不仅考虑到数据处理时的噪声影响,而且对系数矩阵进行了稀疏约束,使其分解出的数据具有较好的语音特征。该算法首先在对语音和噪声的幅度谱先验字典矩阵学习的基础上,构建联合字典矩阵,然后更新带噪语音幅度谱在联合字典矩阵下的系数矩阵,最后重构原始纯净语音,实现语音增强。实验结果表明,在非平稳噪声和低信噪比（小于0 dB）条件下,该算法较好地削弱了噪声的变化对算法性能的影响,不仅有较高的信源失真率（SDR）,提高了1~1.5个数量级,而且运算速度也有一定程度的提高,使得基于非负矩阵分解的语音增强算法更实用。     

基于截断核范数低秩分解的自适应字典学习算法

针对过完备字典直接对图像进行稀疏表示不能很好地剔除高频噪声的影响,压缩感知后图像重构质量不高的问题,提出了基于截断核范数低秩分解的自适应字典学习算法。该算法首先利用截断核范数正则化低秩分解模型对图像矩阵低秩分解得到低秩部分和稀疏部分,其中低秩部分保留了图像的主要信息,稀疏部分主要包含高频噪声及部分物体轮廓信息;然后对图像低秩部分进行分块,依据图像块纹理复杂度对图像块进行分类;最后使用K奇异值分解（K-single value decomposition, K-SVD）字典学习算法,针对不同类别训练出多个不同大小的过完备字典。仿真结果表明,本文所提算法能够对图像进行较好的稀疏表示,并在很好地保持图像块特征一致性的同时显著提升图像重构质量。     

多重约束非负矩阵分解的非平稳噪声语音增强

低信噪比非稳态噪声环境中的语音增强仍是一个开放且具有挑战性的任务. 为了提高传统的基于非负矩阵分解(nonnegative matrix factorization, NMF)的语音增强算法性能, 同时考虑到语音信号的时频稀疏特性和非稳态噪声信号的低秩特性, 本文提出了一种基于多重约束的非负矩阵分解语音增强算法(multi-constraint nonnegative matrix factorization speech enhancement, MC–NMFSE). 在训练阶段, 采用干净语音训练数据集和噪声训练数据集分别构建语音字典和噪声字典. 在语音增强阶段, 在非负矩阵分解目标函数中增加语音分量的稀疏性约束和噪声信号的低秩性约束条件, MC–NMFSE能够更好地从带噪语音中获得语音分量的表示, 从而提高语音增强效果. 通过实验表明, 在大量不同非平稳噪声条件和不同信噪比条件下, 与传统的基于NMF的语音增强方法相比, MC–NMFSE能获得较低的语音失真和更好的非稳态噪声抑制能力.     

多重约束非负矩阵分解的非平稳噪声语音增强（英文）

低信噪比非稳态噪声环境中的语音增强仍是一个开放且具有挑战性的任务.为了提高传统的基于非负矩阵分解(nonnegative matrix factorization,NMF)的语音增强算法性能,同时考虑到语音信号的时频稀疏特性和非稳态噪声信号的低秩特性,本文提出了一种基于多重约束的非负矩阵分解语音增强算法(multi-constraint nonnegative matrix factorization speech enhancement,MC–NMFSE).在训练阶段,采用干净语音训练数据集和噪声训练数据集分别构建语音字典和噪声字典.在语音增强阶段,在非负矩阵分解目标函数中增加语音分量的稀疏性约束和噪声信号的低秩性约束条件,MC–NMFSE能够更好地从带噪语音中获得语音分量的表示,从而提高语音增强效果.通过实验表明,在大量不同非平稳噪声条件和不同信噪比条件下,与传统的基于NMF的语音增强方法相比,MC–NMFSE能获得较低的语音失真和更好的非稳态噪声抑制能力.     

ADMM稀疏非负矩阵分解语音增强算法

提出一种基于交替方向乘子法的（Alternating Direction Method of Multipliers,ADMM）稀疏非负矩阵分解语音增强算法,该算法既能克服经典非负矩阵分解（Nonnegative Matrix Factorization,NMF）语音增强算法存在收敛速度慢、易陷入局部最优等问题,也能发挥ADMM分解矩阵具有的强稀疏性。算法分为训练和增强两个阶段：训练时,采用基于ADMM非负矩阵分解算法对噪声频谱进行训练,提取噪声字典,保存其作为增强阶段的先验信息;增强时,通过稀疏非负矩阵分解算法,从带噪语音频谱中对语音字典和语音编码进行估计,重构原始干净的语音,实现语音增强。实验表明,该算法速度更快,增强后语音的失真更小,尤其在瞬时噪声环境下效果显著。     

基于自适应低秩稀疏分解的超声缺陷回波检测方法

超声无损探伤在金属材料微小缺陷检测中有着广泛的应用,但采集的回波信号通常受到噪声干扰甚至完全被噪声掩盖,为了辨别被噪声干扰的缺陷反射信号,提出了一种基于自适应低秩矩阵分解的超声缺陷回波检测方法。首先对原信号进行短时傅里叶变换并提取幅度谱和相位谱,引入基于误差重建的背景矩阵秩估计方法,用于估计低秩稀疏分解所需的低秩度参数。然后通过低秩稀疏分解将幅度谱分解为低秩、稀疏和噪声三部分,舍弃噪声部分。最后使用时频掩蔽分离出缺陷信号幅度谱并运用逆短时傅里叶变换获得回波信号。应用本文提出的方法分别对仿真和实测信号进行处理,结果表明本方法在缺陷回波检测方面是有效的。     

融合邻域回归和稀疏表示的图像超分辨率重构

对于图像超分辨率重建而言,通常会将图像的整体信息作为研究对象。然而图像本身含有的大量结构信息并没有得到充分利用。为了提高超分辨率重建的效果,实现对不同特征信息的利用,提出了一种融合邻域回归和稀疏表示的图像超分辨率重构算法。依据图像所具有的低秩性对高分辨率图像进行分解,获得高分辨率图像的低秩部分和稀疏部分;将对应的低分辨率图像与高分辨率图像的低秩部分和稀疏部分进行训练,学习得到对应的特征字典;基于高分辨率图像的低秩部分和稀疏部分分别基于稀疏表示和邻域嵌入进行高分辨率重构;基于低秩矩阵恢复理论,融合邻域回归和稀疏表示重构的高分辨率图像,得到最终的高分辨率图像。在测试集Set5和Set14上将提出的算法与几种经典算法进行对比实验,可视化和量化结果均表明,相比传统超分辨率算法,提出的算法在PSNR和SSIM都有很好的提升。     

面向人脸识别的判别低秩字典学习算法

人脸识别是计算机视觉和模式识别领域的一个研究热点,有着十分广泛的应用前景.人脸识别任务在训练样本和测试样本同时包含噪声的情况下存在识别精度不高的问题,为此本文提出一个新的判别低秩字典学习和低秩稀疏表示算法（Discriminative Low-Rank Dictionary Learning for Low-Rank Sparse Representation,DLRD_LRSR）.本文方法在模型中约束每个子字典和稀疏表示低秩避免噪声干扰,并引入了判别重构误差项增强系数的判别性.为验证算法的有效性,本文在3个公开人脸数据集上进行了实验评估,结果表明与现有字典学习算法相比,本文算法能够更好的解决训练样本和测试样本同时存在噪声的人脸识别问题.     

Source cell phone verification from speech recordings using sparse representation

Source recording device recognition is an important emerging research field in digital media forensics. The literature has mainly focused on the source recording device identification problem, whereas few studies have focused on the source recording device verification problem. Sparse representation based classification methods have shown promise for many applications. This paper proposes a source cell phone verification scheme based on sparse representation. It can be further divided into three schemes which utilize exemplar dictionary, unsupervised learned dictionary and supervised learned dictionary respectively. Specifically, the discriminative dictionary learned by supervised learning algorithm, which considers the representational and discriminative power simultaneously compared to the unsupervised learning algorithm, is utilized to further improve the performances of verification systems based on sparse representation. Gaussian supervectors (GSVs) based on MFCCs, which have shown to be effective in capturing the intrinsic characteristics of recording devices, are utilized for constructing and learning dictionary. SCUTPHONE, which is a corpus of speech recordings from 15 cell phones, is presented. Evaluation experiments are conducted on three corpora of speech recordings from cell phones and demonstrate the effectiveness of the proposed methods for cell phone verification. In addition, the influences of number of target examples in the exemplar dictionary and size of the unsupervised learned dictionary on source cell phone verification performance are also analyzed.     

Learning low-rank and discriminative dictionary for image classification

Dictionary learning plays a crucial role in sparse representation based image classification. In this paper, we propose a novel approach to learn a discriminative dictionary with low-rank regularization on the dictionary. Specifically, we apply Fisher discriminant function to the coding coefficients to make the dictionary more discerning, that is, a small ratio of the within-class scatter to between-class scatter. In practice, noisy information in the training samples will undermine the discriminative ability of the dictionary. Inspired by the recent advances in low-rank matrix recovery theory, we apply low-rank regularization on the dictionary to tackle this problem. The iterative projection method (IPM) and inexact augmented Lagrange multiplier (ALM) algorithm are adopted to solve our objective function. The proposed discriminative dictionary learning with low-rank regularization (D²L²R²) approach is evaluated on four face and digit image datasets in comparison with existing representative dictionary learning and classification algorithms. The experimental results demonstrate the superiority of our approach.     

Face recognition based on dictionary learning and subspace learning

Dictionary learning plays an important role in sparse representation based face recognition. Many dictionary learning algorithms have been successfully applied to face recognition. However, for corrupted data because of noise or face variations (e.g. occlusion and large pose variation), their performances decline due to the disparity between domains. In this paper, we propose a face recognition algorithm based on dictionary learning and subspace learning (DLSL). In DLSL, a new subspace learning algorithm (SL) is proposed by using sparse constraint, low-rank technology and our label relaxation model to reduce the disparity between domains. Meanwhile, we propose a high-performance dictionary learning algorithm (HPDL) by constructing the embedding term, non-local self-similarity term, and time complexity drop term. In the obtained subspace, we use HPDL to classify these mapped test samples. DLSL is compared with other 28 algorithms on FRGC, LFW, CVL, Yale B and AR face databases. Experimental results show that DLSL achieves better performance than those 28 algorithms, including many state-of-the-art algorithms, such as recurrent regression neural network (RRNN), multimodal deep face recognition (MDFR) and projective low-rank representation (PLR).     

Time–frequency masking based supervised speech enhancement framework using fuzzy deep belief network

In recent years, deep learning based supervised speech enhancement methods have gained a considerable amount of research attention over the statistical signal processing based methods. In this study, we have considered the time–frequency masking based deep learning framework for speech enhancement and investigated how the performance of these methods can be improved further. We have mainly established that significant performance improvement can be achieved if the deep neural network (DNN) is pre-trained by using Fuzzy Restricted Boltzmann Machines (FRBM) rather than using regular Restricted Boltzmann Machines (RBM). This is mainly because of the fact that the performance of FRBM is more robust and effective when the training data is noisy. In order to train an FRBM, we have adopted a defuzzification method based on the crisp probabilistic mean value of fuzzy numbers. The detailed theory of training strategy of an FRBM with different fuzzy membership functions such as Symmetric Triangular Fuzzy Numbers (STFN) and Asymmetric Triangular Fuzzy Numbers (ATFN) is presented. Furthermore, we have evaluated the performance of the proposed training strategies on different DNN based Speech Enhancement Systems (SES) which are developed based on different training targets such as Complex Ideal Ratio Mask (cIRM), Ideal Ratio Mask (IRM) and Phase-Sensitive Mask (PSM). Experimental results on various noise scenarios have shown that the DNN-based speech enhancement system trained by the proposed approach ensures a consistent improvement in various objective measure scores of perceived speech quality and intelligibility while compared to the conventional DNN-based speech enhancement methods which use regular RBM for unsupervised pre-training.     

结构化低秩字典学习的人脸识别

目的 现实中采集到的人脸图像通常受到光照、遮挡等环境因素的影响,使得同一类的人脸图像具有不同程度的差异性,不同类的人脸图像又具有不同程度的相似性,这极大地影响了人脸识别的准确性。为了解决上述问题对人脸识别造成的影响,在低秩矩阵恢复理论的基础上提出了具有识别力的结构化低秩字典学习的人脸识别算法。方法 该算法基于训练样本的标签信息将低秩正则化以及结构化稀疏同时引入到学习的具有识别力的字典上。在字典学习过程中,首先利用样本的重建误差约束样本与字典之间的关系;其次将Fisher准则应用到稀疏编码过程中,使其编码系数具有识别能力;由于训练样本中的噪声信息会影响字典的识别力,所以在低秩矩阵恢复理论的基础上将低秩正则化应用到字典学习过程中;接着,在字典学习过程中加入了结构化稀疏使其不丢失结构信息以保证对样本进行最优分类;最后再利用误差重构法对测试样本进行分类识别。结果 本文算法在AR以及ORL人脸数据库上分别进行了实验仿真。在AR人脸数据库中,为了分析样本不同维数对实验结果造成的影响,选取了第一时期拍摄的每人6幅图像,包括1幅围巾遮挡,2幅墨镜遮挡以及3幅脸部表情变化以及光照变化（未被遮挡）的图像作为训练样本,同时选取相同组合的样本图像作为测试样本,无论哪种方法,图像的维度越高识别率越高。对比SRC （sparse representation based on classification）算法与DKSVD （discriminative K-means singular value decomposition）算法的识别率可知,DKSVD算法通过字典学习减缓了训练样本中的不确定因素对识别结果的影响;对比DLRD_SR （discriminative low-rank dictionary learning for sparse representation）算法与FDDL （Fisher discriminative dictionary learning）算法的识别率可知,当图像有遮挡等噪声信息存在时,字典低秩化可以提高至少5.8%的识别率;对比本文算法与DLRD_SR算法可知,在字典学习的过程中加入Fisher准则后识别率显著提高,同时理想稀疏值能保证对样本进行最优的分类。当样本图像的维度达到500维时人脸图像在有围巾、墨镜遮挡的情况下识别率可达到85.2%;其中墨镜和围巾的遮挡程度分别可以看成是人脸图像的20%和40%,为了验证本文算法在不同脸部表情变化、光照改变以及遮挡情况下的有效性,根据训练样本的具体图像组合情况进行实验。无论哪种样本图像组合,本文算法在有遮挡存在的样本识别中具有显著优势。在训练样本只包含脸部表情变化、光照变化以及墨镜遮挡图像的情况下,本文算法的识别率高于其他算法至少2.7%,在训练样本只包含脸部表情变化、光照变化以及围巾遮挡图像的情况下,本文算法的识别率高于其他算法至少3.6%,在训练样本包含脸部表情变化、光照变化、围巾遮挡以及墨镜遮挡图像的情况下,其识别率高于其他算法至少1.9%。在ORL人脸数据库中,人脸图像在无遮挡的情况下识别率达到95.2%,稍低于FDDL算法的识别率;在随机块遮挡程度达到20%时,相比较于SRC算法、DKSVD算法、FDDL算法以及DLRD_SR算法,本文算法的识别率最高;当随机块遮挡程度达到50%时,以上算法的识别率均不高,但本文算法的其识别率仍然最高。结论 本文算法在人脸图像受到遮挡等因素的影响时具有一定的鲁棒性,实验结果表明该算法在人脸识别方面具有可行性。     

基于属性自表达的低秩超图属性选择算法*

针对高维数据具有低秩形式和属性冗余等特点,提出一种基于属性自表达的无监督超图属性选择算法。具体地,该算法首先利用属性自表达特点用其他属性稀疏地表达每个属性,此自表达形式使用低秩假设寻找高维数据的低秩表示,然后建立超图正则化因子保持高维数据的局部结构,最后利用稀疏正则化因子进行属性选择。属性自表达特性确定属性的重要性,低秩表示相当于考虑数据的全局信息进行子空间学习,超图正则化因子考虑数据的局部结构对数据进行子空间学习。该算法实际上考虑数据全局和局部信息进行子空间学习,更是一种嵌入了子空间学习的属性选择算法。实验结果表明,该算法相比其它对比算法,能更有效地选取属性,并能取得很好的分类效果。     

基于隐马尔可夫模型的非监督噪声功率谱估计

噪声功率谱估计是语音增强算法的基本组成部分,传统算法大多采用启发式的估计方法,因而不能保证噪声估计值的统计最优。提出了一种基于极大似然的非监督噪声功率谱估计方法,采用隐马尔可夫模型(Hidden Markov model, HMM）在每个子带建立语音和非语音对数功率谱的统计模型,模型包含语音和非语音两个高斯分量,其中非语音高斯分量的均值表示噪声功率谱估计值,根据最大期望（Expectation maximization, EM)算法得到包括噪声均值在内的HMM参数集。针对语音信号可能出现的长时缺失,对HMM引入了一些约束条件,保证了模型的稳定性。实验表明,该方法获得的极大似然噪声估计优于基于启发式的经典方法获得的噪声估计。