语音情感识别研究  

Study of Emotional Speech Recognition

作　　者：章国宝[1] 宋清华[1] 费树岷[1] 赵艳[2] 

机构地区：[1]东南大学自动化学院,江苏南京210096 [2]东南大学信息科学与工程学院,江苏南京210096

出　　处：《计算机技术与发展》2009年第1期92-96,共5页Computer Technology and Development

摘　　要：随着情感信息处理研究的不断深入,人们对语音信号中情感的研究越来越重视。探讨了情感的分类、建模,接着给出语音情感识别系统的总体框架,然后对各个组成部分进行阐述。介绍了现阶段常用特征参数的提取及其有效性分析方法,归纳了比较流行的情感分类算法。对语音情感识别的发展趋势进行了展望。With the development of emotional information processing, the emotional information of speech is gaining more and more attention. In this paper, discuss the category and modeling of emotion firstly; then, give the total frame of the emotional speech recognition system. And explain every parts. Introduce the common methods of feature extraction and contribution analysis, and sum up the popular methods of recognition in this field at home and abroad. Finally, prospect the development of emotional speech recognition in the future.

关 键 词：语音情感 情感分类 特征参数 识别方法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]