基于Fisher准则与SVM的分层语音情感识别

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (456 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对说话人无关的语音情感识别，提出一个分层语音情感识别模型，由粗到细识别悲伤、愤怒、惊奇、恐惧、喜悦和厌恶6种情感。每层采用Fisher比率从288个备选特征中选择适合该层分类的特征，同时将Fisher比率作为输入参数训练该层的支持向量机分类器。基于北京航空航天大学情感语音数据库和德国柏林情感语音数据库，设计4组对比实验，实验结果表明，Fisher准则在两两分类特征选择上优于PCA，SVM在说话人无关的语音情感识别推广方面优于人工神经网络(ANN)。在两个数据库的基础上得到类似结果，说明文中分类模型具有一定的跨文化适应性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	陈立江
	毛峡
	MitsuruISHIZUKA

关键词 ：语音情感识别, 说话人无关, Fisher准则, 支持向量机

Abstract：To solve the speaker independent emotion recognition problem, a multi-level speech emotion recognition system is proposed to classify 6 speech emotions, including sadness, anger, surprise, fear, happiness and disgust from coarse to fine. The key is that the emotions divided by each layer are closely related to the emotional features of speech. For each level, appropriate features are selected from 288 candidate features by Fisher ratio which is also regarded as input parameter for the training of support vector machine (SVM). Based on Beihang emotional speech database and Berlin emotional speech database, principal component analysis (PCA) for dimension reduction and Artificial Neural Network (ANN) for classification are adopted to design 4 comparative experiments, including Fisher+SVM, PCA+SVM, Fisher+ANN, PCA+ANN. The experimental results prove that Fisher rule is better than PCA for dimension reduction, and SVM is more expansible than ANN for speaker independent speech emotion recognition. Good cross-cultural adaptation can be inferred from the similar results of experiments based on two different databases.

Key words： Speech Emotion Recognition Speaker Independent Fisher Criterion Support Vector Machine

收稿日期: 2011-03-21

ZTFLH:

TP391.42

基金资助:国家自然科学基金项目(No.61103097,60873269)、中日国际科技合作项目(No.2010DFA11990)资助

作者简介: 陈立江，男，1984年生，博士研究生，主要研究方向为语音信号处理、情感识别等。E-mail:clj@ee。buaa。edu。cn。毛峡，女，1952年生，教授，博士生导师。主要研究方向为情感计算、模式识别、人机交互等。MitsuruISHIZUKA，男，1949年生，教授，博士生导师，主要研究方向为人机交互、情感计算、仿生代理等。

引用本文:

陈立江，毛峡，MitsuruISHIZUKA. 基于Fisher准则与SVM的分层语音情感识别[J]. 模式识别与人工智能, 2012, 25(4): 604-609. CHEN Li-Jiang, MAO Xia, Mitsuru ISHIZUKA. Multi-Level Speech Emotion Recognition Based on Fisher Criterion and SVM. , 2012, 25(4): 604-609.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/ 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2012/V25/I4/604

[1] Johnson W F,Emde R N,Scherer K R,et al.Recognition of Emotion from Vocal Cues.Arch Gen Psychiatry,1986,43(3): 280-283
[2] Park C H,Sim K B.Emotion Recognition and Acoustic Analysis from Speech Signal // Proc of the International Joint Conference on Neural Networks.Portland,USA,2003,IV: 2594-2598
[3] Banziger T,Scherer K R.The Role of Intonation in Emotional Expressions.Speech Communication,2005,46(3/4): 252-267
[4] Mao Xia,Chen Lijiang,Fu Liqin.Multi-Level Speech Emotion Recognition Based on HMM and ANN // Proc of the WRI World Congress on Computer Science and Information Engineering.Los Angeles,USA,2009,VII: 225-229
[5] Schuller B,Rigoll G,Lang M.Speech Emotion Recognition Combining Acoustic Features and Linguistic Information in a Hybrid Support Vector Machine-Belief Network Architecture // Proc of the IEEE International Conference on Acoustics,Speech and Signal Processing.Montreal,Canada,2004,I: 577-580
[6] Mao Xia,Chen Lijiang.Speech Emotion Recognition Based on Parametric Filter and Fractal Dimension.IEICE Trans on Information and Systems,2010,93(8): 2324-2326
[7] Liu Jia,Chen Chun,Ye Chengxi,et al.Speech Emotion Recognition Based on Covariance Descriptor and Riemannian Manifold.Pattern Recognition and Artificial Intelligence,2009,22(5): 673-677 (in Chinese)
(刘佳,陈纯,叶承羲,等.基于协方差描述子和黎曼流形的语音情感识别.模式识别与人工智能,2009,22(5): 673-677)
[8] Tomkins S S.Affect,Imagery,Consciousness.New York,USA: Springer,1962
[9] Ekman P.An Argument for Basic Emotions.Cognition and Emotion,1992,6(3/4): 169-200
[10] Izard C E.Human Emotions.New York,USA: Plenum Press,1977
[11] Wundt W M.Grundzuge der Physiologischen Psychologie.5th Edition.Leipzig,Germany: Engelmann,1874
[12] Guo Yuefei,Shu Tingting,Yang Jingyu,et al.Feature Extraction Method Based on the Generalised Fisher Discriminant Criterion and Facial Recognition.Pattern Analysis Applications,2001,4(1): 61-66
[13] Wang S,Li Deyu,Wei Yingjie,et al.A Feature Selection Method Based on Fisher’s Discriminant Ratio for Text Sentiment Classification // Proc of the International Conference on Web Information Systems and Mining.Shanghai,China,2009: 88-97
[14] Lin Yilin,Wei Gang.Speech Emotion Recognition Based on HMM and SVM // Proc of the 4th International Conference on Machine Learning and Cybernetics.Guangzhou,China,2005,VIII: 4898-4901
[15] Lu Tao.Speech Emotion Recognition Based on SVM.Master Dissertation.Yanshan,China: Yanshan University,2007 (in Chinese)
(芦涛.基于SVM的汉语语音情感识别研究.硕士学位论文.燕山:燕山大学,2007)
[16] Cortes C,Vapnik V.Support-Vector Networks.Machine Learning,1995,20(3): 273-297
[17] Mao Xia,Chen L J,Zhang Bing.Mandarin Speech Emotion Recognition Based on a Hybrid of HMM/ANN.International Journal of Computers,2007,4(1): 321-324
[18] Burkhardt F,Paeschke A,Rolfes M,et al.A Database of German Emotional Speech // Proc of Interspeech.Lissabon,Portugal,2005: 1517-1520