计算机技术与发展2016，Vol.26Issue(5)：27-30,35,5.DOI:10.3969/j.issn.1673-629X.2016.05.006
多模式情感识别特征参数融合算法研究
Research on Feature Fusion Algorithm for Multimodal Emotion Recognition
摘要
Abstract
In order to overcome the limitation of single mode emotion recognition,a novel multimodal emotion recognition algorithm is proposed,taking speech signal and facial expression signal as the research subjects. First,the speech signal feature and facial expression signal feature is fused,and sample sets by putting back sampling are obtained,and then sub-classifiers are acquired by Adaboost algo-rithm. Second,the difference is measured between two classifiers by double error difference selection strategy. Finally,the recognition re-sult is obtained by the majority voting rule. Experiments show the method improves the accuracy of emotion recognition by giving full play to the advantages of decision level fusion and feature level fusion,and makes the whole fusion process close to human emotion rec-ognition more,with a recognition rate 91. 2%.关键词
多模式/情感识别/语音信号/面部表情信号Key words
multimodal/emotion recognition/speech signal/facial expression signal分类
信息技术与安全科学引用本文复制引用
韩志艳,王健..多模式情感识别特征参数融合算法研究[J].计算机技术与发展,2016,26(5):27-30,35,5.基金项目
国家自然科学基金资助项目(61403042,61503038) （61403042,61503038）
辽宁省教育厅项目(L2013423) （L2013423）
