[1]张前进,王华东.基于核典型相关分析和支持向量机的语音情感识别模型[J].南京理工大学学报(自然科学版),2017,41(02):191.[doi:10.14177/j.cnki.32-1397n.2017.41.02.009]
 Zhang Qianjin,Wang Huadong.Speech emotion recognition model based on kernel canonicalcorrelation analysis and support vector machine[J].Journal of Nanjing University of Science and Technology,2017,41(02):191.[doi:10.14177/j.cnki.32-1397n.2017.41.02.009]
点击复制

基于核典型相关分析和支持向量机的语音情感识别模型()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年02期
页码:
191
栏目:
出版日期:
2017-04-30

文章信息/Info

Title:
Speech emotion recognition model based on kernel canonicalcorrelation analysis and support vector machine
文章编号:
1005-9830(2017)02-0191-07
作者:
张前进1王华东2
1.安徽国防科技职业学院 信息工程系,安徽 六安 237011; 2.周口师范学院 计算机科学与技术学院,河南 周口 466001
Author(s):
Zhang Qianjin1Wang Huadong2
1.Department of Information Engineering,Anhui Vocational College of Defense Technology,Lu’an 237011,China; 2.School of Computer Science and Technology,Zhoukou Normal University,Zhoukou 466001,China
关键词:
语音情感识别 核典型相关分析 特征选择 情感分类器 支持向量机
Keywords:
speech emotion recognition kernel canonical correlation analysis feature selection emotion classifiers support vector machine
分类号:
TP391
DOI:
10.14177/j.cnki.32-1397n.2017.41.02.009
摘要:
为了获得更好的语音情感识别的实时性和正确率,该文提出了基于核典型相关分析和支持向量机的语音情感识别模型。首先提取多种情感识别的特征,采用核典型相关分析对特征进行选择,将选择的特征作为支持向量机的输入向量进行训练,建立情感识别的分类器,最后采用语音情感识别的标准数据库进行验证性和对比实验。实验结果表明,该模型能够准确识别不同类型的语音情感,获得较高的语音情感识别率。核典型相关分析减少了分类器的输入向量数,加快了情感识别速度,获得了理想的实时性。该文语音情感识别结果优于对比模型,具有更高的实际应用价值。
Abstract:
In order to obtain the better real-time and correct rate of the speech emotion recognition,an emotion recognition model based on the kernel canonical correlation analysis and the support vector machine is proposed here.Firstly,multiple features of the speech emotion recognition are extracted and the feature selection is selected by the kernel canonical correlation analysis,and then the selected features are taken as the input vector of the support vector machine to be trained for establishing the classifier of the speech emotion recognition.Finally,experiments on the standard database of the speech emotion recognition is used to validate the performance of the model.The experimental results show that,by using the kernel canonical correlation analysis with the less input vectors,the proposed model can accurately identify the emotion type and increase the recognition rate of the speech emotion,and has the better read-time.The result of the speech emotion recognition is better than that of the contrast models,and the model has the higher practical application value.

参考文献/References:

[1] Jaimes A,Sebe N.Multimodal human-computer interaction:A survey[J].Computer Vision and Image Understanding,2007,108(1):116-134.
[2]罗宪华,杨大利,徐明星.面向非特定人的语音情感识别特征研究[J].北京信息科技大学学报,2011,26(2):72-76.
Luo Xianhua,Yang Dali,Xu Mingxing.Speaker-independent oriented research on features of speech emotion recognition[J].Journal of Beijing Information Science and Technology University,2011,26(2):72-76.
[3]Wang Yongjin,Guan Ling.Recognizing human emotional state from audiovisual signals[J].IEEE Transactions on Multimedia,2008,10(5):936-946.
[4]Zeng Zhihong,Tu Jilin,Pianfetti B M,et al.Audio-visual affective expression recognition through multistream fused HMM[J].Multimedia,IEEE Transactions on,2008,10(4):570-577.
[5]温万惠,刘光远,熊勰.基于生理信号的二分类情感识别系统特征选择模型和泛化性能分析[J].计算机学,2011,38(5):220-223.
Wen Wanhui,Liu Guangyuan,Xiong Xie.Feature selection model and generalization performance of two-class emotion recognition systems based on physiological signal[J].Computer Science,2011,38(5):220-223.
[6]屠彬彬,于凤芹.基于样本熵与MFCC融合的语音情感识别[J].计算机工程,2012,38(7):142-144.
Tu Binbin,Yu Fengqin.Speech emotion recognition based on fusion of sample entropy and MFCC[J].Computer Engineering,2012,38(7):142-144.
[7]余华,黄程韦,张潇,等.混合蛙跳算法神经网络及其在语音情感识别中的应用[J].南京理工大学学报,2011,35(5):659-663.
Yu Hua,Huang Chengwei,Zhang Xiao,et al.Shuffled frog leaping algorithm based neural network and its application in speech emotion recognition[J].Journal of Nanjing University of Science and Technology,2011,35(5):659-663.
[8]Qin Yuqiang,Zhang Xueying.SVM-based emotional recognition for speech signal[J].Journal of Circuits and Systems,2012,17(5):55-59.
[9]陶华伟,柳晶晶,梁瑞宇,等.面向语音情感识别的Gabor分块局部二值模式特征[J].信号处理,2016,32(5):505-510.
Tao Huawei,Liu Jingjing,Liang Ruiyu,et al.Gabor block spectrum features based on local binary pattern for speech emotion recognition[J].Signal Processing,2016,32(5):505-510.
[10]陈俊,王爱国,王坤侠,等.基于类依赖的语音情感特征选择[J].微电子学与计算机,2016,33(8):92-96.
Chen Jun,Wang Aiguo,Wang Kunxia,et al.Speech emotion recognition with class-dependent feature selection methods[J].Microelectronics & Computer,2016,33(8):92-96.
[11]陈红,刘光远,赖祥伟.相关性分析和最大最小蚁群算法用于脉搏信号的情感识别[J].计算机学,2012,39(4):250-255.
Chen Hong,Liu Guangyuan,Lai Xiangwei.Affective recognition from pulse signal using correlation analysis and max-min ant colony algorithm[J].Computer Science,2012,39(4):250-255.
[12]张潇丹,包永强,奚吉,等.基于MD-CM-SFLA神经网络的耳语音情感识别[J].东南大学学报(自然科学版),2012,42(5):848-853.
Zhang Xiaodan,Bao Yongqiang,Xi Ji,et al.Whispered speech emotion recognition based on MD-CM-SFLA neural network[J].Journal of South East University(Natural Science Edition),2012,42(5):848-853.
[13]李书玲,刘蓉,张鎏钦,等.基于改进型SVM算法的语音情感识别[J].计算机应用,2013,33(7):1938-1941.
Li Shuling,Liu Rong,Zhang Liuqin,et al.Speech emotion recognition algorithm based on modified SVM[J].Journal of Computer Applications,2013,33(7):1938-1941.
[14]秦宇强,张雪英.基于SVM的语音信号情感识别[J].电路与系统学报,2012,17(5):55-59.
Qin Yuqiang,Zhang Xueying.SVM-based emotional recognition for speech signal[J].Journal of Circuits and Systems,2012,17(5):55-59
[15]Zhang Zhao,Zhao Mingbo,Chow T W S.Binary-and multi-class group sparse canonical correlation analysis for feature extraction and classification[J].IEEE Transactions on Knowledge and Data Engineering,2013,25(10):2192-2205.
[16]Sun Tingkai,Chen Songkan.Locality preserving CCA with applications to data visualization and pose estimation[J].Image and Vision Computing,2007,25(5):531-543.
[17]Ye Qiaolin,Ye Ning,Yin Tongming.Enhanced multi-weight vector projection support vector machine[J].Pattern Recognition Letters,2014,42(1):91-100.
[18]Zhang Zhao,Chow T W S.Maximum margin multisurface support tensor machines with application to image classification and segmentation[J].Expert Systems with Applications,2012,39(1):849-860.
[19]Gu Zhenfeng,Zhang Zhao,Sun Jiabao.Robust image recognition by L1-norm twin-projection support vector machine[J].Neurocomputing,2017,223:1-11.

备注/Memo

备注/Memo:
收稿日期:2016-12-27 修回日期:2017-03-06
基金项目:2016年安徽省高等学校自然科学研究重点项目(KJ2016A120)
作者简介:张前进(1982-),男,硕士,讲师,主要研究方向:人工智能、数据挖掘,E-mail:zh-qj@foxmail.com; 通讯作者:王华东(1977-),男,硕士,副教授,主要研究方向:人工智能、数据挖掘,E-mail:46935563@qq.com.。
引文格式:张前进,王华东.基于核典型相关分析和支持向量机的语音情感识别模型[J].南京理工大学学报,2017,41(2):191-197.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2017-04-30