A Method of Feature Selection of Voice Content Classification Based on Analysis of Variance in Orthogonal Experiments

Abstract:

In view of the performance of dividing the audio category is closely related to the speech feature parameters selected,a systematic and practical characteristic parameter selection method is presented,orthogonal experimental design method based on analysis of variance.This method has better characteristic [1],the construction of the experiment is simple and the result is easy to analysis,it’s also has directive function to the subsequent experiments.We first do the feture parameters and the level selection,then select amount of appropriate points with representative and typical from a large number of experimental points to construct the orthogonal table to do a analysis of variance by mathematical statistics and orthogonal principle,finding the optimal feature combination. In this pater,the experimental corpus that is voice content is divided into two categories,the kind of traffic and the legal category.Comparing the experimental results shows that the method is not only effective to do feature parameter selection in voice content classification but also has direct meaning to the subsequent experiment design and research.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 4133-4138
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.4133
• Online since: May 2014
• Authors: Si An*, Xin Hua Fan
• Keywords: Analyasis of Variance, Audio Classification, Feature Selection, Orthogonal Experimental Design, Parameter Optimization

References

[1] YANG Da-Li, XU Ming-Xing, WU Wen-Hu. Study of Feature Selection for Speech Rccognition[J]. JOURNAL OF COMPUTER RESEARCH AND DEVELOPMENT. 2003, 40(7): 963-939.

[2] XIE Yan-lu, WU Li-fu, DAI Ber-qian, LI Hui. Classification Speaker Verification System with Short Speech Based on SVM Fusing Scores[J]. Journal of Data Acquisition & Processing. 2005, 20(2): 213-217.

[3] C Emmanouilidis, A Hunter. Multi-objective evolutionary setting for feature selection and a commonality –based crossover operator [A] . Proceedings of the IEEE Conference on Evolutionary Computation [ C] . Piscat-away : Institute of Electrical and Electronics Engineers Inc, 2000. 309 -316.

DOI: 10.1109/cec.2000.870311

[4] Council on modern application mathematics handbook. Modern application mathematics handbook ( Volume: probability statistics and random process) [ M ] . Beijing : T sin ghua University Press, (2000).

[5] Ho S Y，Lin H，Li W H, et al． Orthogonal particles swarm Optimization and its application to task assignment problems [J]. IEEE Transactions on Systems, Man and Cybernetics, 2008, 38(2) : 288－298.

DOI: 10.1109/tsmca.2007.914796

[6] Li X L，Zhao Q，Zhang C J. Research on multiple index optimization method of the orthogonal test design[C] / IEEE International Conference on Computer Science and Information Technology. [s. l. ]: [s. n. ], 2010: 224－226.

[7] ZHAI Guo-fu, LIANG Hui-min, WANG Hao, Liu Xiao-zhou, Wang Li-Zhong, LIU Mao-Kai. RESEARCH ON THE PARAMETERS OPTIMUM DESIGN OF POLARIZED MAGNETIC SYSTEM BASED ON ORTHOGONAL DESIGN[J]. Proceedings of the CSEE. 2003, 23(10): 158-163.

[8] Liang X B．Orthogonal designs with maximal rates[J], IEEE Transactions on Information, 2003, 49(10) : 2468-2503.

[9] HE Qing-wei, LI Hui, XU Min-qiang. Speaker Cerification Based on Pitch Classified Feature Mapping[J]. Communications Technology, 2010, 43(3): 147-149.