实用语音情感识别中的若干关键技术  

Key Technologies in Practical Speech Emotion Recognition

作　　者：赵力[1] 黄程韦[1] 

机构地区：[1]东南大学信息科学与工程学院,南京210096

出　　处：《数据采集与处理》2014年第2期157-170,共14页Journal of Data Acquisition and Processing

基　　金：国家自然科学基金(61273266;61231002;61375028;61301219;61301295)资助项目;教育部博士点专项基金(20110092130004)资助项目;江苏省自然科学基金(ZKJ201202)资助项目

摘　　要：介绍了语音情感识别领域的最新进展和今后的发展方向,特别是介绍了结合实际应用的实用语音情感识别的研究状况。主要内容包括:对情感计算研究领域的历史进行了回顾,探讨了情感计算的实际应用;对语音情感识别的一般方法进行了总结,包括情感建模、情感数据库的建立、情感特征的提取,以及情感识别算法等;结合具体应用领域的需求,对实用语音情感识别方法进行了重点分析和探讨;分析了实用语音情感识别中面临的困难,针对烦躁等实用情感,总结了实用情感语音语料库的建立、特征分析和实用语音情感建模的方法等。最后,对实用语音情感识别研究的未来发展方向进行了展望,分析了今后可能面临的问题和解决的途径。The latest and future progress in speech emotion recognition is introduced, especially in the practical speech emotion research considering the real world applications. The followings are mainly discussed. The history and development of affective computing research, the practi- cal applications in affective computing, and the review of general speech emotion recognition methods, including emotion model, emotion database, feature extraction and emotion recogni- tion algorithm. Considering the needs in real world applications, the key technologies in practi- cal speech emotion research are focused on. Moreover, the current challenges in practical speech emotion recognition are analyzed, especially for the fidgetiness emotion, and the meth- ods in database establishment, feature analysis and modeling techniques are reviewed. Finally, the outlook of future speech emotion research is given, and the future challenges and possible solutions are discussed.

关 键 词：实用语音情感识别 情感计算 特征分析 情感模型 语料库 识别方法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]