语音情感识别的研究进展  

A survey of emotion recognition in speech

作　　者：林奕琳[1] 韦岗[1] 杨康才 

机构地区：[1]华南理工大学电子与信息学院,广东广州510640 [2]深圳市公安局科技处,广东深圳518001

出　　处：《电路与系统学报》2007年第1期90-98,共9页Journal of Circuits and Systems

基　　金：国家自然科学基金资助项目(60172048)

摘　　要：情感在人类的感知、决策等过程扮演着重要角色。长期以来情感智能研究只存在于心理学和认知科学领域,近年来随着人工智能的发展,情感智能跟计算机技术结合产生了情感计算这一研究课题,这将大大的促进计算机技术的发展。情感自动识别是通向情感计算的第一步。语音作为人类最重要的交流媒介,携带着丰富的情感信息。如何从语音中自动识别说话者的情感状态近年来受到各领域研究者的广泛关注。本文从语音情感识别所涉及的几个重要问题出发,包括情感理论及情感分类、情感语音数据库、语音中的情感特征和语音情感识别算法等,介绍了当前的研究进展,并讨论了今后研究的几个关键问题。Emotions play a significant role in human perception and decision making. For a long time research on emotion intelligence has been done in the fields of psychology and cognitive science. Along with the development of artificial intelligence these years, the combination of emotion intelligence and computer technology brings the research area of affective computing, Automatic recognition of human emotion is the first step toward affective computing. Speech as the most important medium of human communication contains lots of emotional information, and how to automatically recognize speakers＇ emotional state is the subject of attention by researchers from different fields. This paper surveys the current state of the art in several key issues related to emotion recognition by speech, including the theory of emotion, the collecting of emotional speech database, the emotional speech feature, and the recognition algorithm. Finally several key issues for future research are presented.

关 键 词：语音 情感 语音情感识别 

分 类 号：TN912.3[电子电信—通信与信息系统]