loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
18th International Conference on Pattern Recognition (ICPR'06) Volume 2
A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants as Acoustic Models
Hong Kong
August 20-August 24
ISBN: 0-7695-2521-0
ASCII Text
x 
 
Edin Andelic, Martin Schaffoner, Marcel Katz, Sven E. Kruger, "A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants as Acoustic Models," Pattern Recognition, International Conference on, vol. 2, pp. 1158-1161, 18th International Conference on Pattern Recognition (ICPR'06) Volume 2, 2006.
 
 
BibTex
x
 
@article{ 10.1109/ICPR.2006.82,
author = {Edin Andelic and Martin Schaffoner and Marcel Katz and Sven E. Kruger},
title = {A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants as Acoustic Models},
journal ={Pattern Recognition, International Conference on},
volume = {2},
year = {2006},
issn = {1051-4651},
pages = {1158-1161},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICPR.2006.82},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Pattern Recognition, International Conference on
TI - A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants as Acoustic Models
SN - 1051-4651
SP1158
EP1161
A1 - Edin Andelic,
A1 - Martin Schaffoner,
A1 - Marcel Katz,
A1 - Sven E. Kruger,
PY - 2006
VL - 2
JA - Pattern Recognition, International Conference on
ER -
 
Edin Andelic, Cognitive Systems Group, IESK Otto-von-Guericke-University, Germany
Martin Schaffoner, Cognitive Systems Group, IESK Otto-von-Guericke-University, Germany
Marcel Katz, Cognitive Systems Group, IESK Otto-von-Guericke-University, Germany
Sven E. Kruger, Cognitive Systems Group, IESK Otto-von-Guericke-University, Germany
In this paper we propose a novel order-recursive training algorithm for kernel-based discriminants which is computationally efficient. We integrate this method in a hybrid HMM-based speech recognition system by translating the outputs of the kernel-based classifier into class-conditional probabilities and using them instead of Gaussian mixtures as production probabilities of a HMM-based decoder for speech recognition. The performance of the described hybrid structure is demonstrated on the DARPA Resource Management (RM1) corpus.
Citation:
Edin Andelic, Martin Schaffoner, Marcel Katz, Sven E. Kruger, "A Hybrid HMM-Based Speech Recognizer Using Kernel-Based Discriminants as Acoustic Models," icpr, vol. 2, pp.1158-1161, 18th International Conference on Pattern Recognition (ICPR'06) Volume 2, 2006
Usage of this product signifies your acceptance of the Terms of Use.