期刊文献+

基于SVM的语音特征提取及识别模型研究 被引量:3

Research on Speech Feature Extraction and Recognition Model Based on SVM
下载PDF
导出
摘要 针对非特定文本的说话人识别,研究了特征提取方法及SVM核函数和参数选取对识别结果的影响,分析了现有的语音特征提取算法及各自的优缺点,以及不同核函数、核参数及惩罚参数对识别性能的影响.采用改进的网格寻优方法,进一步提高语音信息的识别时间. The paper chose a fold that a non-specific text speaker identification. The paper focused on feature extraction methods and SVM kernel function and parameter selection on the identification re-suits, focusing on analysis of the existing voice feature extraction algorithms , their advantages and disadvantages, different kernel function, kernel parameters and penalty parameters on the recognition performance. Grid search method is introduced in order to improve the recognition time.
出处 《武汉理工大学学报(交通科学与工程版)》 2014年第2期316-319,共4页 Journal of Wuhan University of Technology(Transportation Science & Engineering)
基金 国家自然科学基金项目资助(批准号:51211130307)
关键词 支持向量机(SVM) 特征参数 核函数 识别模型 网格寻优算法 support vector machine (SVM) feature Extraction kernel function recognition model grid search method
  • 相关文献

参考文献8

  • 1XUE Hui, YANG Qiang, CHEN Songcan. SVM: Support vector machines, in The top ten algorithms in data mining[M]. Boca Raton: CRC Press, 2010.
  • 2MALDONADO S,WEBER R, BASAK J. Simultane- ous feature selection and classification using kernel- penalized support vector machines [J]. Information Sciences, 2011,181(1) : 115-128.
  • 3VLADIMIR N V. The nature of statistical learning theory[D]. New York:Springer, 1999.
  • 4ARUN K M, GOPAL M. Reduced one-against-all method formulticlass SVM classification[J]. Expert Systems with Application, Acta Electronica Sinica, 2010,38(7):1626-1633.
  • 5吴艳艳.孤立词语音识别的关键技术研究[D].青岛:青岛大学,2012.
  • 6叶庆云,蒋佳.基于语音MFCC特征的改进算法[J].武汉理工大学学报,2007,29(5):150-152. 被引量:9
  • 7邓乃杨,田英杰.支持向量机:理论、算法与拓展[M].北京:科学出版社,2009.
  • 8刘新宇,黄德启.基于SVM分类器的道路湿滑图像分类方法研究[J].武汉理工大学学报(交通科学与工程版),2011,35(4):784-787. 被引量:8

二级参考文献13

  • 1Andreas K, Wilco B. Winter road condition recogni- tion using video image classification[C]//Source: Transportation Research Record 1627, 1998 National Research Council: 29-33.
  • 2Muneo Y, Koji U, Isao H, Shin Y, Sadayuk T. De- tection of wet-road conditions from images captured by a vehicle-mounted camera [J]. Rob Mechatron, 2005,17(3): 269-276.
  • 3Caporali B E, Castelli F, Lorenzini C. Field analysis of the water film dynamics on a road pavement[J]. Phys. Chem. Earth (C), 2001,26:717-722.
  • 4U.S. Department of Transportation Federal High- way Administration. Final report on signal and im- age processing for road condition classification[R]. Aerotech Telub and Dalarma University, 2002.
  • 5Fukui H, Takagi J, Murata Y, Takeuchi M. An im- age processing method to detect road surface condi- tion usingoptical spatial frequency [J]. Intelligent Transportation System. IEEE Conference on, 1997. ITSC97 :1005-1009.
  • 6Wang Weifeng, Wu Qing, Chu Xiumin, Wu Yong. Discussion to information acquisition technology and safety identification method of traffic environment [J]. Pacific-Asia Workshop on Computational Intel- ligence and Industrial Application, 2008,12 : 874-878.
  • 7Hsu Chih-Wei, Lin Chih-Jen. A comparison of meth- ods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks, 2002,13: 415-425.
  • 8Burges J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowl- edge Discovery, 1998,2(2) :1- 47.
  • 9Delaney B,Jayant N,Hans M,et al.A Low-power,Fixed-point Front-end Feature Extraction for a Distributed Speech Recognition System[J].HP Laboratories Technical Report,2001,26(9):252-254.
  • 10Christophe L,Georges L,Nocera P,et al.Reducing Computational and Memory Cost for Cellular Phone Embedded Speech Recognition System[J].Proceedings of the IEEE,1997,85(9):112-115.

共引文献24

同被引文献25

引证文献3

二级引证文献50

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