Dr. Samir Elmougy-1-conf - King Saud University Repository

advertisement
Title
Author-s
Contact
information
Department
Major
Citation
Year of
Publication
Publisher
Sponsor
Type of
Publication
ISSN
URI/DOI
Full Text
(Yes,No)
Key words
Abstract
A comparison of combined classifier architectures for Arabic Speech
Recognition
Essa, E.M. Tolba, A.S. Elmougy, S
mougy@ksu.edu.sa, Telephone number 00966-01-4695205, Dept. of
Computer Science, College of Computer and Information Sciences,
King Saud University,
Computer Science,
Computer Science,
2008
IEEE Explorer - Proceeding of International Conference on Computer
Engineering & Systems, ICCES 2008., Pages(s): 139 – 153, Cairo,
EGYPT, 2008
Conference
http://ieeexplore.ieee.org/Xplore/login.jsp?url=http%3A%2F%2Fieeexp
lore.ieee.org%2Fstamp%2Fstamp.jsp%3Ftp%3D%26arnumber%3D477
2985&authDecision=-203
Yes
Combined classifiers offer solution to the pattern classification problems
which arise from variation of the data acquisition conditions, the signal
representing the pattern to be recognized and classifier architecture
itself. This paper studies the effect of classifier architecture on the
overall performance of the Arabic Speech Recognition System. Five
different proposed combined classifier architectures are studied and a
comparison of their performance is conducted. Boosting is another type
of combined classifier to improve the performance of almost any
learning algorithm. We investigate the effect of combining Neural
Networks by AdaBoost.M1 and propose an enhancement for
AdaBoost.M1 algorithm. It is found that the proposed enhanced
AdaBoost.M1 outperforms either the architectures based on ensemble
approaches or the modular approaches.
Download