TY  - BOOK
AU  - Omar Abdallah Abdelfatah Elgendy
AU  - Abdelkarim S. Omar Hassan , 
AU  - Ahmed Abdelnaby Ahmed Mahmoud , 
AU  - Moataz Mohamed Hatem Elayadi , 
TI  - Speaker identification using minimum volume ellipsoids and large-margin criterion / 
PY  - 2015///
CY  - Cairo : 
PB  - Omar Abdallah Abdelfatah Elgendy , 
KW  - Discriminative Training
KW  - Speaker Identification
KW  - Statistical Pattern Recognition
N1  - Thesis (M.Sc.) - Cairo University - Faculty of Engineering - Department of Mathematics and Physics; Issued also as CD
N2  - This thesis proposes two approaches building robust text-independent speaker identification systems in noisy environments. The first approach is based using robust statistical estimators such as the Minimum Volume Ellipsoid and Minimum Covariance Determinant to improve the maximum likelihood based classifiers by making them robust to outliers. The second approach is based on using an improved version for the large-margin discriminative criterion, which is characterized by its simplicity compared to the standard large-margin approach and other discriminative approaches. Experimental results show that our proposed techniques outperform the baseline techniques
ER  -