语音情感中基于ZCPA的VAP模型

摘要

分析一个基于心理学的情感空间模型原理.研究语音情感识别中7种情感(中性、喜悦、愤怒、惊讶、恐惧、悲伤和厌恶)的效价-激励-能量(VAP)维分布状况,根据过零峰值幅度(ZCPA)的最大值、最小值、均值和绝对值方差和,在VAP三维空间中分析维数水平和ZCPA韵律特征之间的关系.实验结果表明,该情感空间模型原理有助于描述和区分各种语音情感.%This paper presents a conception of emotion space modeling using psychological research for reference. Based on this conception, this paper studies the Valence-Arousal-Power(VAP) distribution of the seven emotions for speech emotional recognition, including joy, anger, surprise, fear, disgust, sadness and neutral, in the three dimensional space of VAP, and analyses the relationship between the dimensional ratings and the Zero Crossings with Peak Amplitudes(ZCPA) prosodic characteristics in terms of maximum, minimum, mean and absolute square difference sum of ZCPA. Experimental results show that the conception of emotion modeling is helpful to describe and distinguish speech emotions.