基于SVM-GMM的开集说话人识别方法

建立一种支持向量机-高斯混合模型(SVM-GMM),用以提高开集说话人识别的识别率。该模型的基本思想是将SVM的分类结果用GMM模型进行确认。由于SVM模型具有较好的分类性能,而GMM模型能够较好地描述类别内部的相似性,因此这2个模型的组合能够优势互补,从而获得较好的识别效果。实验结果表明,使用SVM-GMM模型能有效地提高开集说话人识别的识别率。     

基于形状感应的运动目标跟踪算法

Mean-Shift算法无法自动跟踪目标,且对目标形状要求较苛刻。针对该问题,提出一种基于形状感应的运动目标跟踪算法,采用混合高斯分布对背景建模,协助Mean-Shift算法自动定位初始目标,增加描述形状的协方差参数,使跟踪能感受到目标形状的变化。实验结果表明,该算法基本解决了自动定位问题及形状变化问题,在保证实时性的前提下,跟踪准确度提高40%以上。     

BagGMM: Calling copy number variation by bagging multiple Gaussian mixture models from tumor and matched normal next-generation sequencing data

Copy number variations (CNVs) contribute significantly to human genomic variability, some of which lead to diseases. However, effective detection of CNVs from whole genome next generation sequencing data (NGS) remains challenging. Here, we present BagGMM, a new method to call CNVs using tumor-normal matched samples from NGS data. BagGMM extracts read depth ratios of tumor samples to normal samples, divides the genomic sequences into segments by sliding windows to count the average coverage ratio of each segment, filters candidate deletions and duplications based on a coarse criterion of coverage ratio, and then builds Gaussian Mixture Model (GMM) for remaining ratios to identify the remaining ambiguous copy number states after filtration. Bagging multiple GMMs makes false positive calls descent instead of using one GMM, thus enhancing the detection power of BagGMM. Considering the computation speed of GMMs and false positive calls, we employ a segmentation procedure “large window and then small windows”, which is also helpful to determine boundary of CNV regions. We apply BagGMM to three simulation datasets and two groups of human whole genome sequencing (WGS) data for breast cancer patients and ovarian cancer patients to identify CNVs, respectively. All performed experiments demonstrate that BagGMM has the capability of robustly identification of CNVs with different sizes and states. The performance of this tool is compared to four peer existing CNV detection methods. BagGMM shows a significant improvement in both sensitivity and specificity for detecting both copy number gains and losses.     

弓张式GMM发音振子径向磁场仿真分析

超磁致伸缩材料(GMM)发音振子是骨传导听觉装置的核心部件,该文提出了一种弓张式的GMM发音振子结构,并利用ANSYS软件对其内部磁场径向分布进行了有限元仿真和分析。结果表明,振子中间部分磁场强度和均匀性最好,弓张结构磁导率的变化对两端磁场分布的均匀性影响较大,为满足磁场强度和均匀性要求,弓张结构应优先选用镍铁合金材料。     

FEM COUPLING FIELD ITERATION AND ITS CONVERGENCE FOR A GMM ACTURATOR

The coupling iteration (CI) of the finite element method(FEM) is used to simulate the magnetic and mechanical characteristics for a GMM actuator. The convergent ability under different prestress and different load types is investigated. Then the calculated deformations are compared with the experimental values. The results convince that the CI of FEM is suitable for the simulation of energy coupling and transformation mechanism of the GMM. At last, the output deformation properties are studied under different input currents, showing that there is a good compromise between good linearity and large strain under the prestress 6 MPa.     

考虑帧间信息的语音转换算法

传统的加权频率卷绕算法是单独地对每帧语音特征参数进行转换,没有考虑到语音帧前后的相关信息.针对这一点,该文提出了一种改进的加权频率卷绕算法,它利用压缩感知理论提取语音信号的帧间相关信息.在进行转换时,该算法是相当于对语音段进行转换.客观测试和主观听觉评测表明,虽然改进后算法的性能会受到语音段长度的影响,但当选择合适语音段长度时,性能要好于传统的加权频率卷绕算法.     

一种新的分维高斯混合模型语音转换方法

高斯混合模型在语音转换中得到了广泛应用,但其随着模型阶数和特征维数的提高,估计参数的数目会急剧增加,使参数估计的准确性和稳定性大为降低。本文提出将特征向量去相关之后,将向量之间的转换转化为标量之间的转换,以此来减少估计参数个数。实验表明,采用该方法的语音转换算法能有效改善转换语音的性能。     

GMM模型在核能谱平滑滤波中的应用

结合核能谱的统计特性,采用高斯混合模型(Gaussian mixture model,GMM)对核能谱进行平滑滤波处理。其基本思想是:利用GMM模型良好的逼近能力对核能谱进行函数逼近,为原始能谱曲线建立基于GMM的数学模型,在该模型的多次运算过程中实现更合理的平滑滤波。     

一种改进的高斯混合模型算法

建立声学模型是说话人识别技术的重要环节，一种好的建模方法对说话人识别系统的识别率具有极其重大的影响。本文介绍了一种改进的高斯混合模型算法——将聚类算法与传统高斯混合模型结合起来的建模方法，并对此种建模方法得出的识别效果与传统的高斯混合模型进行了比较。从对比结果可以看出，基于聚类的高斯混合模型的说话人识别相对于传统的高斯混合模型在识别率上有所提高。     

一种基于肤色模型的贝叶斯人脸检测算法

为了结合颜色信息和人脸特征构造快速高精度的人脸检测系统，提出一种基于肤色模型的贝叶斯人脸检测算法，新算法包括两大步骤，即肤色检测和人脸特征检测．前者借助混合高斯模型对人脸肤色区域楚模．生成肤色检测规则．同时，针对合理选择混合高斯模型中分量数问题，提出一种基于聚类有效性函数的最优分量数确定方法，以提高肤色检测的精度，在人脸特征区域判决中引入菱形搜索，与贝叶斯判决相结合，以提高人脸特征区域的检测速度，新算法具有较高的检测精度和较低的漏警率，同时能够满足实时检测的要求。