Enhancements of SVM Speaker Recognition by Dynamic Time Wrapping

Ing Jr Ding; Da Cheng Ou

doi:10.4028/www.scientific.net/AMM.764-765.891

Paper Titles

Design and Implementation of Cloud-Dust Based Intelligent System
p.872

Design of Cloud Load Balance Architecture for Web Servers
p.877

Development of Cloud-Dust Based Intelligent Maximum Power Analysis System for Photovoltaic
p.881

Energy-Efficient 2-Covered Path Routing for Distributed Wireless Sensor Networks with Variable Transmission Ranges
p.886

Enhancements of SVM Speaker Recognition by Dynamic Time Wrapping
p.891

Enhancing the Effect on Project Success through Information Presentation
p.895

ET Detector: A Client-Based Solution to Detect an Evil Twin Access Point
p.900

Evaluation of Traffic Data Collection Method
p.905

FCA-Based Data Analysis for Discovering Association Rules in Social Network Service
p.910

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 764-765Enhancements of SVM Speaker Recognition by Dynamic...

Enhancements of SVM Speaker Recognition by Dynamic Time Wrapping

Abstract:

This paper proposes an approach using dynamic time wrapping (DTW) to improve the classification performance of the SVM separation hyperplane. The presented method by incorporating the distance information derived from DTW template matching calculations into SVM separation hyperplane training will be able to effectively control the balance between mar-gin maximization and the amount of misclassifications, and therefore the recognition accuracy of the SVM classifier on speaker recognition will further be increased. Experimental results demonstrated the effectiveness and efficiency of the developed approach.

You might also be interested in these eBooks

Modern Design Technologies and Experiment for Advanced Manufacture and Industry

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 764-765)

Pages:

891-894

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.764-765.891

Citation:

Cite this paper

Online since:

May 2015

Authors:

Ing Jr Ding*, Da Cheng Ou

Keywords:

Dynamic Time Wrapping, Recognition Performances, Speaker Recognition, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] S. K. Gaikwad, B. W. Gawali, P. Yannawar: A review on speech recognition technique, Int. J. Comput. Appl. 10 (2010) 16-24.

Google Scholar

[2] I. J. Ding, C. T. Yen: Enhancing GMM speaker identification by incorporating SVM speaker verification for intelligent web-based speech applications, Multimed. Tools Appl. (2013).

DOI: 10.1007/s11042-013-1587-5

Google Scholar

[3] C. J. C. Burges: A tutorial on support vector machines for pattern recognition, Data Min. Knowl. Disc. 2 (1998) 121-167.

Google Scholar

[4] J. X. Dong, A. Krzyzak, C. Y. Suen: Fast SVM training algorithm with decomposition on very large datasets, IEEE Trans. Pattern Anal. Mach. Intell. 27 (2005) 603-618.

DOI: 10.1109/tpami.2005.77

Google Scholar

[5] S. Z. Boujelbene, D. B. A. Mezghani, N. Ellouze: Improving SVM by modifying kernel functions for speaker identification task, International Journal of Digital Content Technology and its Applications 4 (2010) 100-105.

DOI: 10.4156/jdcta.vol4.issue6.12

Google Scholar

[6] H. Sakoe, S. Chiba: Dynamic programming algorithm optimization for spoken word recognition, IEEE Trans. Acoust. Speech Signal. Process. 26 (1978) 43-49.

DOI: 10.1109/tassp.1978.1163055

Google Scholar