DocumentCode
2455863
Title
Feature Transformation and Model Design Using Minimum Classification Error
Author
Ratnagiri, M.V. ; Rabiner, L. ; Biing-Hwang Juang
Author_Institution
Dept. of Electr. & Comput. Eng., State Univ. of Rutgers, NJ, USA
fYear
2010
fDate
12-14 Dec. 2010
Firstpage
797
Lastpage
802
Abstract
A Minimum Classification Error (MCE) based recognition system that also estimates a global feature transformation matrix has been implemented. Unlike earlier studies, we make the explicit assumption that the covariance matrix of the Gaussian mixtures is diagonal when estimating the transformation matrix. This is necessary for mathematical consistency between the model and the transformation matrix estimates. Experimental results show a reduction of up to 50% in the word error rate as compared to Maximum Likelihood estimation.
Keywords
Gaussian processes; covariance matrices; maximum likelihood estimation; speech recognition; Gaussian mixtures; covariance matrix; global feature transformation matrix; maximum likelihood estimation; minimum classification error; speech recognition system; Computational modeling; Covariance matrix; Feature extraction; Hidden Markov models; Maximum likelihood estimation; Noise; feature transformation; speech processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Applications (ICMLA), 2010 Ninth International Conference on
Conference_Location
Washington, DC
Print_ISBN
978-1-4244-9211-4
Type
conf
DOI
10.1109/ICMLA.2010.122
Filename
5708945
Link To Document