Emotion recognition from speech is an important field of research in human computer interaction. In this letter the framework of Support Vector Machines (SVM) with Gaussian Mixture Model (GMM) supervector is introduce...Emotion recognition from speech is an important field of research in human computer interaction. In this letter the framework of Support Vector Machines (SVM) with Gaussian Mixture Model (GMM) supervector is introduced for emotional speech recognition. Because of the importance of variance in reflecting the distribution of speech, the normalized mean vectors potential to exploit the information from the variance are adopted to form the GMM supervector. Comparative experiments from five aspects are conducted to study their corresponding effect to system performance. The experiment results, which indicate that the influence of number of mixtures is strong as well as influence of duration is weak, provide basis for the train set selection of Universal Background Model (UBM).展开更多
传统阈值法难以及时准确地辨识出运行设备的劣化状态,针对风力发电机组实施状态检修工作的要求,提出一种风机变桨系统劣化状态在线辨识方法。在阐述风机变桨控制原理和变桨系统监测参数的基础上,建立了以风速、有功功率为输入,风轮转速...传统阈值法难以及时准确地辨识出运行设备的劣化状态,针对风力发电机组实施状态检修工作的要求,提出一种风机变桨系统劣化状态在线辨识方法。在阐述风机变桨控制原理和变桨系统监测参数的基础上,建立了以风速、有功功率为输入,风轮转速、3个叶片的桨距角和变桨驱动电流为输出的非线性多输入多输出(multi input multi output,MIMO)系统回归模型。将系统特征向量实测值与最小二乘支持向量机(least square support vector machines,LSSVM)回归计算结果间的偏离定义为系统"观测值"。接着采用高斯混合模型(Gaussian mixture model,GMM)拟合多维观测值的分布,并利用风机数据采集与监控系统(supervisory control and data acquisition,SCADA)中的数据计算系统劣化指数,实现系统状态的在线辨识。最后,以一台发生过变桨轴承保持架和滚动体损坏故障的风机为对象,进行了实例验证,证明了所建模型的准确性和有效性。展开更多
基金Supported by the National Natural Science Foundation of China (No. 61105076)Natural Science Foundation of Anhui Province of China (No. 11040606M127) as well as Key ScientificTechnological Project of Anhui Province (No. 11010202192)
文摘Emotion recognition from speech is an important field of research in human computer interaction. In this letter the framework of Support Vector Machines (SVM) with Gaussian Mixture Model (GMM) supervector is introduced for emotional speech recognition. Because of the importance of variance in reflecting the distribution of speech, the normalized mean vectors potential to exploit the information from the variance are adopted to form the GMM supervector. Comparative experiments from five aspects are conducted to study their corresponding effect to system performance. The experiment results, which indicate that the influence of number of mixtures is strong as well as influence of duration is weak, provide basis for the train set selection of Universal Background Model (UBM).
文摘传统阈值法难以及时准确地辨识出运行设备的劣化状态,针对风力发电机组实施状态检修工作的要求,提出一种风机变桨系统劣化状态在线辨识方法。在阐述风机变桨控制原理和变桨系统监测参数的基础上,建立了以风速、有功功率为输入,风轮转速、3个叶片的桨距角和变桨驱动电流为输出的非线性多输入多输出(multi input multi output,MIMO)系统回归模型。将系统特征向量实测值与最小二乘支持向量机(least square support vector machines,LSSVM)回归计算结果间的偏离定义为系统"观测值"。接着采用高斯混合模型(Gaussian mixture model,GMM)拟合多维观测值的分布,并利用风机数据采集与监控系统(supervisory control and data acquisition,SCADA)中的数据计算系统劣化指数,实现系统状态的在线辨识。最后,以一台发生过变桨轴承保持架和滚动体损坏故障的风机为对象,进行了实例验证,证明了所建模型的准确性和有效性。
