基于PAD模型的级联分类情感语音识别  

Cascaded Classification Emotional Speech Recognition Based on PAD Model

作　　者：张雪英 张婷 孙颖 张卫 ZHANG Xueying;ZHANG Ting;SUN Ying;ZHANG Wei(College of Information and Computer,Taiyuan University of Technology,Jinzhong Shanxi 030600,China)

机构地区：[1]太原理工大学信息与计算机学院,山西晋中030600

出　　处：《太原理工大学学报》2018年第5期731-735,共5页Journal of Taiyuan University of Technology

基　　金：国家自然科学基金资助项目(61371193)

摘　　要：针对声学特征(韵律特征和MFCC特征)对情感语音的分类识别性能不理想的问题,提出了一种将声学特征与情感语音PAD数据相结合的级联分类方法用于情感语音识别。首先提取情感语音的声学特征,对特征分别单独识别与组合识别,对比建立最优特征集合。然后将声学特征组合与情感语音PAD数据相结合,分两步逐级地判断出输入语音所属的情感类型。该方法在TYUT2.0情感语音数据库上得到了较好的结果,情感分类识别率相较于传统声学特征的分类识别率提高了15.4%.In view of the problem that the combination of acoustic features(prosodic feature and MFCC feature)is not ideal for the classification and recognition of emotional speech,a cascade classification method for emotional speech recognition that combines acoustic features with emotional speech PAD data is proposed.First,the acoustic features of emotional speech are extracted,and the features are subject to separate recognition and combined identification,and the optimal characteristic set is established by comparison.Then the acoustic feature combination and emotional speech PAD data are combined to determine the emotion type of the input speech step by step.The result of this method is better in TYUT2.0 emotional speech database.The recognition rate of sentiment classification is 15.4%higher than that of traditional acoustic features.

关 键 词：PAD模型 级联分类 声学特征 支持向量机 情感语音识别 

分 类 号：TN912.3[电子电信—通信与信息系统]