More Web Proxy on the site http://driver.im/

Paper Titles

Design of Automatic Detection System for Temperature Sensor Based on LabVIEW
p.626

Design of a Multi-Mode Asymmetric Waveform Generator for FAIMS
p.631

Analysis of Displacement Monitoring Measurement in Tunnel Construction
p.635

Study on Fuzzy Inference Method for Fault Diagnosis Expert System
p.639

A Novel Preprocessing Method for Palm Vein
p.643

Research on Recognition of Pathological Voice by AD Tree
p.647

A Modified MUSIC Algorithm for DOA Estimation
p.652

The analysis of 3-Level Charge Pumping in SOHOS Flash Memory
p.658

Application Research of rCOS-Based Trusted Requirement Engineering
p.662

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 658Research on Recognition of Pathological Voice by...

Research on Recognition of Pathological Voice by AD Tree

Article Preview

Abstract:

This paper mainly studies on the classification of pathological voice from normal voice based on the sustained vowel /a/. Firstly, the original 18 acoustic features are extracted. Then on the basis of the extracted parameters, this paper recognizes the pathological voice using AD Tree. During the classification stage, the cross-validation of features is also as references in the process. This method is validated with a sound database provided by the Massachusetts Eye and Ear Infirmary (MEEI). After the 10 fold cross-validation, comparing with 7 other kinds of classifiers, the experimental results show that AD Tree can get the highest recognition rate of 95.2%. The method in this paper shows that all the extracted parameters are reasonable in the following recognition process and AD tree is a good recognition way in pathological voice research.

You might also be interested in these eBooks

Materials and Manufacturing Research

Info:

Periodical:

Advanced Materials Research (Volume 658)

Pages:

647-651

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.658.647

Citation:

Cite this paper

Online since:

January 2013

Authors:

Jun Jie Zhu, Xiao Jun Zhang, Ji Hua Gu, He Ming Zhao, Qiang Zhou, Zhi Tao

Keywords:

AD Tree, MEEI, Pathological Voice, Speech Recognition

Export:

RIS, BibTeX

Price:

Permissions:

Request Permissions

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] C. Jo. Engineers and Computer Scientists, Vol. 2(2010), p.1271.

[2] K. Umapathy and S. Krishnan. Med. Biol. Eng. Comput. (2005), p.457.

[3] S. Imaizumi. Acoustics, Speech and Signal Processing. (1986), p.677.

[4] P. Mitev and S. Hadjitodorov. Information Sciences, Vol. 156(2003), p.3.

[5] S. Siegel and N. J. Castellan. New York. (1988).

[6] X. H. Wang, P. Shu and L. Cao. Computer Science, vol. 37 (2010), p.240.

[7] D. Trandabat. Intelligent System Design and Applications(2011), p.1062.

[8] L. H. Luan and G. L. Ji. Computer Engineering, vol. 30(2004), p.94.

[9] B. S. Yang, T. J. Wang, L. Chang, D. Q. Yang and S. W. Tang: submitted to Journal of Computer Research and Development( 2007).