期刊文献+

多分类器融合在语音情感识别中的应用 被引量:3

Speech emotion recognition using ensemble methods
在线阅读 下载PDF
导出
摘要 针对语音情感识别问题,提出一种采用决策模板的多分类器融合方法,利用不同类型的声学特征子集来构造子分类器。不同的子集能充分提高各子分类器之间的"多样性"指标,这是多分类器融合算法能够成功应用的必备条件。与多数投票融合算法和支持向量机相比该方法取得了较好的识别结果。另一方面,从多样性指标分析的角度出发探究该方法能获得较好识别效果的原因。 This paper proposes a novel scheme for speech emotion recognition,which uses Decision Templates(DT) ensemble algorithm to combine base classifiers built on acoustic feature subsets.Different feature subsets can provide sufficient diversity among base classifiers,which is known as a necessary condition for improvement in ensemble performance.Compared with those methods of Majority Voting ensemble and Support Vector Machine,the ensemble scheme proposed in this paper can achieve the highest performance.On the other hand,this paper investigates the possible reasons why ensemble systems can provide potential performance,in terms of diversity analysis.
出处 《计算机工程与应用》 CSCD 北大核心 2010年第28期205-207,235,共4页 Computer Engineering and Applications
关键词 语音情感识别 多分类器融合 决策模板 多样性分析 speech emotion recognition ensemble decision templates diversity analysis
作者简介 毕福昆(1982-),男,博士研究生,研究领域为模式识别;E—mail:bifukun@bit.edu.cn 边明明(1985-),男,博士研究生,研究领域为信号与信息处理,实时信号处理。
  • 相关文献

参考文献12

  • 1陈建厦,李翠华.语音情感识别的研究进展[J].计算机工程,2005,31(13):35-37. 被引量:8
  • 2Morrison D,Wang R,De Siliva L C,et al.Real-time spoken affect classification and its application in call-centres[C]//Information Technology and Applications(ICITA'2005),2005,1: 483-487.
  • 3Morrison D, Wang R,Xu W L.Voting ensemble for spoken affect classification[J].Journal of Network and Computer Application, 2008.
  • 4Liscombe J, Venditti J, Hirschberg J.Classifying subject ratings of emotional speech using acoustic features[C]//Proc of Euro Speech, 2003 : 725-728.
  • 5Burkhardt F, Paeschke A, Rolfes M, et al.A database of German emotional speech[C]//Interspeech-2005,2005:1517-1520.
  • 6Kuncheva L I.Decision templates for multiple classifier fusion: An experimental comparison[J].Pattern Recognition, 2001,34: 299-314.
  • 7王治平,赵力,邹采荣.Support vector machines for emotion recognition in Chinese speech[J].Journal of Southeast University(English Edition),2003,19(4):307-310. 被引量:8
  • 8Schuller B,Rigoll G.Timing levels in segment-based speech emotion recognition[C]//ICSLP, 2006 : 1818-1821.
  • 9徐翔俊,毕福昆,杨鉴.基于支持向量机的民族语口音识别[J].计算机工程与应用,2008,44(13):71-73. 被引量:5
  • 10Banfield R E.Ensembte diversity measures and their application to thinning[J].Information Fusion,2005(6):49-62.

二级参考文献8

  • 1胡懋智,古红英.各种不同类型的支持向量机及其性能比较分析[J].计算机工程与应用,2005,41(12):37-40. 被引量:8
  • 2Li Y, Zhao Y. Recognizing Emotions in Speech Using Shortterm and Long-term Features. In: Proc. ICSLP, 1998:2255-2258.
  • 3Nicholson J, Takahashi K, Nakatsu R. Emotion Recognition in SpeechUsing Neural Networks. Neural Information Processing, Proceedings,ICONIP '99, 6^th International Conference, 1999,2:495 -501.
  • 4New T L, Wei F S, Silva L C D. Speech Based Emotion Classification.Electrical and Electronic Technology, TENCON. Proceedings of IEEE Region 10 International Conference, 2001,1:297 -301.
  • 5Schuller B, Rigoll G, Lang M. Hidden Markov Model-based Speech Emotion Recognition. Acoustics, Speech, and Signal Processing,Proceedings. (ICASSP '03). 2003 IEEE International Conference,2003,2:1-4.
  • 6Christopher J.C. Burges. A Tutorial on Support Vector Machines for Pattern Recognition[J] 1998,Data Mining and Knowledge Discovery(2):121~167
  • 7赵力,钱向民,邹采荣,吴镇扬.语音信号中的情感识别研究[J].软件学报,2001,12(7):1050-1055. 被引量:56
  • 8卢坚,陈毅松,孙正兴,张福炎.语音/音乐自动分类中的特征分析[J].计算机辅助设计与图形学学报,2002,14(3):233-237. 被引量:26

共引文献18

同被引文献29

引证文献3

二级引证文献15

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部