实际语音盲分离客观评价指标研究

由于没有可比对的语音源信号,如何评价实际语音盲分离的效果非常困难。目前还没有相应的客观评价指标。将语音特征引入实际语音盲分离评价指标,提出了基于信号相关性和Mel倒谱系数高斯混合模型的听觉-独立性联合指标,客观评价了实际语音盲分离的性能。     

青年群体社会责任感影响因素的实证研究

本文旨在以60后、70后、80后青年群体作为研究对象,采用广义矩估计GMM模型的研究方法,对影响中国青年社会责任感的各方面因素进行剖析。研究结果显示,国家教育环境、青年受教育程度、青年就业状况与青年社会责任感之间存在正相关关系,而精神信仰缺失度与其存在负相关关系,但影响因素在不同时期的显著性水平存在差异。     

A Novel Ni/YSZ Anode Image Segmentation Method for Solid Oxide Fuel Cell Electrodes Microstructure

For the three‐phase identification of solid oxide cuel cell (SOFC) electrode, this paper presents a novel segmentation method based on gaussian mixture model (GMM) for YSZ/Ni anode optical microscopy (OM) images. A coarseness‐entropy adaptive factor is defined to incorporate the spatial information based on markov random field (MRF) into GMM. Furthermore, the proposed method can obtain the trade‐off between robustness to noise and effectiveness of preserving the details. Experimental results show that the proposed method outperforms the compared method on three‐phase microstructure identification. It can provide reliable foundation for the quantification of SOFC microstructure parameters.     

对MFCC进行GMM聚类的汉语数字识别方法

汉语数字识别常用MFCC作为特征,针对0-9十个数字MFCC样本特征数据量大的问题,提出了用GMM模型对提取的特征参数MFCC的数据进行聚类来减少数据量,以GMM模型参数中的均值作为新的特征,采用动态规划算法进行汉语数字语音识别.仿真实验表明,进行GMM特征变换后的新特征数据为MFCC的30.9％,系统运行时间减少了2...     

基于基元段特征和GMM的源-目标说话人F0～t转换

基音轨迹F_0～t转换是实现高质量源-目标说话人声音转换的重要组成部分。本文给出了一种与说话内容无关的F_0～t转换方法,为了在与文本无关的前提下,提取出尽可能反映说话人个性特征的基音起伏的较长时的信息,本文采用了从n个短时帧组成的基元段提取特征矢量,并以基元段矢量为单元进行转换,采用了基于高斯混合模型(GMM)的概率加权转换算法使每个特征矢量的转换规则是由多个类规则的线性加权组合得到的,从而提高了转换精度,同时还解决了一般分类器中处于类边界数据的分类错误。实验表明,基于基元段特征矢量和GMM的转换方法具有很好的效果。     

基于两层分块GMM-PRS的流程工业过程运行状态评价

过程运行状态评价旨在实时判断运行性能优劣程度,并追溯导致非优运行状态的原因,指导操作人员进行生产调整,保证企业经济效益.因此,对过程运行性能优劣评价的研究具有重要的理论和应用价值.本文针对定量、定性变量共存的流程工业过程运行状态评价问题,提出基于两层分块混合模型的评价方法.将流程工业过程根据其物理特性和管理方向划分子块,产生子块层和全流程层.在定量信息占主导地位的子块内,建立定量的高斯混合模型（Gaussian mixture model,GMM）.在定性信息占主导地位的子块内,建立定性概率粗糙集（Probabilistic rough set,PRS）模型.综合各子块运行状态信息,进一步判定全流程运行状态等级.针对非优运行状态等级,本文提出基于贡献率的非优原因追溯方法,在非优子块内进行原因追溯.最后,将所提方法应用于某黄金湿法冶炼生产过程,说明所提方法的可行性和有效性.     

基于Level set方法的医学图像分割

本文引入了一种基于偏微分方程的曲线进化方法—Level set方法,通过与Fast marching方法的结合,可以实现运算速度的大大提高。同时引进了更有效的Kim提出的GMM(Group Marching Method)方法,减少了运算量,并给出了改进方法。最后,把该方法用于仿真图与医学图像分割中,获得了较好的效果。     

Brainwave Classification for Character-Writing Application Using EMD-Based GMM and KELM Approaches

A brainwave classification, which does not involve any limb movement and stimulus for character-writing applications, benefits impaired people, in terms of practical communication, because it allows users to command a device/computer directly via electroencephalogram signals. In this paper, we propose a new framework based on Empirical Mode Decomposition (EMD) features along with the Gaussian Mixture Model (GMM) and Kernel Extreme Learning Machine (KELM)-based classifiers. For this purpose, firstly, we introduce EMD to decompose EEG signals into Intrinsic Mode Functions (IMFs), which actually are used as the input features of the brainwave classification for the character-writing application. We hypothesize that EMD along with the appropriate IMF is quite powerful for the brainwave classification, in terms of character applications, because of the wavelet-like decomposition without any down sampling process. Secondly, by getting motivated with shallow learning classifiers, we can provide promising performance for the classification of binary classes, GMM and KELM, which are applied for the learning of features along with the brainwave classification. Lastly, we propose a new method by combining GMM and KELM to fuse the merits of different classifiers. Moreover, the proposed methods are validated by using the volunteer-independent 5-fold cross-validation and accuracy as a standard measurement. The experimental results showed that EMD with the proper IMF achieved better results than the conventional discrete wavelet transform (DWT) feature. Moreover, we found that the EMD feature along with the GMM/KELM-based classifier provides the average accuracy of 77.40% and 80.10%, respectively, which could perform better than the conventional methods where we use DWT along with the artificial neural network classifier in order to get the average accuracy of 80.60%. Furthermore, we obtained the improved performance by combining GMM and KELM, i.e., average accuracy of 80.60%. These outcomes exhibit the usefulness of the EMD feature combining with GMM and KELM based classifiers for the brainwave classification in terms of the Character-Writing application, which do not require any limb movement and stimulus.     

TD-SCDMA系统终端中的GMM功能实体研究

移动性管理(MM,MobilityManagement)是层3的一个子层,它主要完成与用户的移动性相关的一些功能。根据业务的分域划分,MM子层被分为支持CS模式的MM实体和支持PS模式的GMM实体。本文通过对GMM一般过程和特殊过程的描述,介绍了TD-SCDMA系统终端GMM实体的功能及其实现过程。     

基于大跨空间网架结构主动控制的新型超磁致伸缩材料作动器优化配置研究

首先基于新型超磁致伸缩材料(GMM)设计了一种新型作动器,并对其进行了试验研究,获得了其本构方程.利用结构振动模态方程提出了遗传优化算法中的主要参数——优化性能指标;利用MATLB所提供的遗传算法工具箱并结合前述结论确定了作动器最优布置位置.最后利用所编制的LQR主动控制程序对一平板网架结构进行了不布置及随机布置与优化布置该作动器下的地震响应对比分析.结果表明:优化布置该新型作动器后结构地震响应明显减弱,从而验证了该新型作动器在结构主动控制中应用的有效性及遗传优化算法对于此类问题进行研究的可行性.