计算机工程与应用2017，Vol.53Issue(3)：7-11,153,6.DOI:10.3778/j.issn.1002-8331.1606-0447
使用二次特征选择及核融合的语音情感识别
Speech emotion recognition using secondary feature selection and kernel fusion
摘要
Abstract
To improve the recognition performance of speech emotion recognition, a high dimension acoustic feature set is constructed by basic acoustic features. A secondary feature selection method comprehensively considering the inherent properties between the features and emotions is adopted to select optimal subset with effective emotional recognizability. In the emotion recognition procedure, a binary tree structured multi-class classifier model is adopted to make compromise between total performance and complexity of the system. Kernel fusion method is utilized in SVM model to improve the recognition of the most confusable emotion. The experimental results of five emotions in Berlin database verify the effec-tiveness of the combination of secondary feature selection and kernel fusion on the improvement of emotional recognition accuracies and its robustness on noisy samples.关键词
情感识别/支持向量机/特征选择Key words
emotion recognition/support vector machine/feature selection分类
信息技术与安全科学引用本文复制引用
姜晓庆,夏克文,林永良..使用二次特征选择及核融合的语音情感识别[J].计算机工程与应用,2017,53(3):7-11,153,6.基金项目
国家自然科学基金(No.61501204) （No.61501204）
河北省自然科学基金(No.E2016202341) （No.E2016202341）
河北省引进留学人员基金(No.C2012003038) （No.C2012003038）
山东省自然科学基金(No.ZR2015FL010) （No.ZR2015FL010）
济南大学科研基金(No.XKY1317). （No.XKY1317）
