基于改进多核学习的语音情感识别算法  

Speech Emotion Recognition Based on Modified Multiple Kernel Learning Algorithm

作　　者：奚吉[1] 赵力[2] 左加阔[2] 

机构地区：[1]常州工学院计算机信息工程学院,常州213002 [2]东南大学信息科学与工程学院,南京210096

出　　处：《数据采集与处理》2014年第5期730-734,共5页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61375028;61301219)资助项目;江苏省自然科学基金(BK20130241)资助项目

摘　　要：提出一种基于改进多核学习的语音情感识别算法。算法以高斯径向基核函数为基准,通过采样不同的样本,采用不同的评价标准并获得不同的参数,来提高分类性能。此外,通过引入多核技术,将得到的高斯核函数构建多核学习的基核,并通过利用松弛因子构建的软间隔多核学习的目标函数改善了学习效率。对比仿真实验结果表明,本文提出的基于多核学习语音情感识别算法有效提高了语音情感识别性能。An improved algorithm of speech emotion recognition is proposed based on modified multiple kernel learning. The algorithm based on Gaussian radial basis function improves classification performance by gathering different samples, utilizing different evaluation criteria and acquiring different parameters . In addition, with the help of multiple kernel technology, the trained Gauss kernel functions are used to construct the basis of multiple kernel learning and the efficiency of learning are greatly improved by utilizing the relaxation factor to construct objective function of soft margin . Experimental results show the presented algorithm can effectively improve the performance of speech emotion recognition.

关 键 词：语音情感识别 多核学习 支持向量机 

分 类 号：TN912.3[电子电信—通信与信息系统]