期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2015
卷号：10
期号：11
页码：33-42
DOI：10.14257/ijmue.2015.10.11.04
出版社：SERSC
摘要：Based on the studies of the emotional feature, a new method based on the emotional feature analysis for emotion recognition in speech signal characteristics is proposed. Collected from 10 speakers with joy, anger, surprise and sad emotion statement, a total of 3000 sentences, 10 emotion characteristics extracted from these speech data. According to the experiments in speech emotion corpus using different classifiers, the proposed method can both achieve relatively better performance than the state-of-the-art dimensionality reduction methods and 92.5% of the average emotional recognition rate is obtained. The future work will be focused on searching for more effective emotional characteristic parameter and recognition method.
