Consonant recognition of dysarthria based on wavelet transform and fuzzy support vector machines

被引：5
作者：
Chen Z.-M. [1 ]
Ling W.-X. [2 ]
Zhao J.-H. [2 ]
Yao T.-T. [1 ]
机构：
[1] The First Affiliated Hospital, Jinan University, Guangzhou
[2] School of Science, South China University of Technology, Guangzhou
来源：
Journal of Software | 2011年 / 6卷 / 05期
关键词：
Consonant recognition; Fuzzy theory; Support vector machines; Wavelets transform;
D O I：
10.4304/jsw.6.5.887-893
中图分类号：
学科分类号：
摘要：
Consonant(in Chinese) recognition had important clinical significance in the assessment of dysarthria, while the consonants were so short and unstable that the recognition results of traditional methods were ineffective. The algorithm described in this paper extracted a new feature(DWTMFC-CT) of the consonants employing wavelet transformation, and the difference of similar consonants can be described more accurately by the feature. Then the algorithm classified consonants using multi-class fuzzy support vector machines(FSVM). In order to reduce the computation complexity caused by using the standard fuzzy support vector machines for multi-class classification, this paper proposed a algorithm based on two stages. Experimental results shown that the proposed algorithm could get better classification results while reducing the training time greatly. © 2011 ACADEMY PUBLISHER.
引用
收藏
页码：887 / 893
页数：6
相关论文
共 14 条
  • [1] Shi W.U., Evgeny Bovbel.Application of modified wavelet features and multi-class SVM to pathological vocal detection, Journal of Computer Applications, 18, 8, pp. 2097-2100, (2008)
  • [2] Ji L., Vilda G.P., Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors, IEEE Trans on Biomedical Engineering, 51, 2, pp. 380-384, (2004)
  • [3] Nan Y., Ge Y., A new approach of the statistical analysis and recognition for the unstable phonetic structure, Pattern Recognition and Artificial Intelligence, 15, 3, pp. 270-273, (2002)
  • [4] Tursun N., Silamu W., Uyghur continuous speech recognition system based on HMM, Journal of Computer Applications, 29, 7, pp. 2009-2011, (2009)
  • [5] Bing-Xi W., Dan Q.U., Xuan P., Basis of Practical Speech Recognition, (2005)
  • [6] Lan T., Xiao-Shan L.U., Shu-Zhong B., Speakerindependent speech recognition based on a fast NN algorithm, Control and Decision, 17, 1, pp. 65-68, (2002)
  • [7] Yong-Jie Z., Pu H., Dong-Feng W., Guo-peng W., Sisk function based sum algorithm Diagnosis its application to a slight malfunction, Proceedings of the Csee, 23, 9, pp. 198-203, (2003)
  • [8] Li Q.I., Yu-Shu L.I.U., Fuzzy Support Vector Machine Based on Two Stage Clustering, Computer Engineering, 34, 1, pp. 4-6, (2008)
  • [9] Chihwei H., Chihjen L., A comparison of methods for multi-class support vector machines, IEEE Trans on Neural Networks
  • [10] Jun Z., De-Yun Z., Peng F., Objective Speech Quality Evaluation Based on Fuzzy Multi-Class Support Vector Machine, Journal of xi an Jiaotong University, 40, 2, pp. 199-202, (2006)
12