CORC  > 清华大学
基于情感分数曲线的语音情感变化检测
徐露 ; 徐明星
2010-07-15 ; 2010-07-15
会议名称第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会论文摘要集 ; Abstract Book of the 10~(th) National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing ; 第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会 ; The 10~(th) the National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing ; 中国甘肃兰州 ; CNKI ; 中国中文信息学会语音信息专业委员会、中国声学学会语言、听觉和音乐声学分会、中国语言学会语音学分会
关键词语音识别 情感识别 情感计算 变化检测 speech recognition emotion recognition affective computing variation detection TP391.41
其他题名Emotion Score Curve based Speech Emotion Change Detection
中文摘要在实际应用中,语音情感变化的检测比单纯的语音情感识别具有更广泛的应用前景,而目前关于语音情感变化检测的研究却很少。为了实现语音情感变化检测,本文研究了基于情感分数曲线的检测方法。首先将情感语音划分成一些语音段,采用基于频谱特征的方法进行情感识别,得到情感分数曲线。然后根据情感分数曲线的变化规律,确定发生情感变化的时间范围。针对该方法正确率较低的问题,对其进行了分析和改进,改进后的方法可以达到86.1%的正确率,并且具有比较稳定的检测性能。; For practical application, the emotional variation detection of speech has more extensive applying prospect than sin- gle emotional speech recognition. However, there are only few researches on this subject at present. This paper researches a method based on emotion score curves which achieves the emotional variation detection of speech. Firstly, the raw speech is divided into some segments. Then a method based on spectral features is used to recognize each emotional speech segment and several score curves are obtained. Finally, the time range of emotional variation is detected according to the changing law of score curves. Because of the problem of nonideal detection accuracy, the above method is analyzed further. Experimental results demonstrate that the improved method has the accuracy of 86.1% and its performance is relatively stable.; 国家自然科学基金重点项目(60433030)
会议录出版者清华大学
语种中文 ; 中文
内容类型会议论文
源URL[http://hdl.handle.net/123456789/70079]  
专题清华大学
推荐引用方式
GB/T 7714
徐露,徐明星. 基于情感分数曲线的语音情感变化检测[C]. 见:第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会论文摘要集, Abstract Book of the 10~(th) National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing, 第十届全国人机语音通讯学术会议暨国际语音语言处理研讨会, The 10~(th) the National Conference on Man-Machine Speech Communication (NCMMSC'2009) and International Symposium on Speech and Language Processing, 中国甘肃兰州, CNKI, 中国中文信息学会语音信息专业委员会、中国声学学会语言、听觉和音乐声学分会、中国语言学会语音学分会.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace