Mohamed Kamal Omar

29 papers A 12Misc 9Journal 2Unranked 5
YearRankTypeTitle / Venue / Authors
2016 — conf
A factor analysis model of sequences for language recognition.
SLT
Mohamed Kamal Omar
2015 Misc conf
Fast approximate i-vector estimation using PCA.
ICASSP
Mohamed Kamal Omar
2014 A conf
Robust language identification using convolutional neural network features.
INTERSPEECH
Sriram Ganapathy, Kyu Jeong Han, Samuel Thomas, Mohamed Kamal Omar, Maarten Van Segbroeck, Shrikanth S. Narayanan
2014 Misc conf
Shift-invariant features for speech activity detection in adverse radio-frequency channel conditions.
ICASSP
Mohamed Kamal Omar, Sriram Ganapathy
2013 A conf
TRAP language identification system for RATS phase II evaluation.
INTERSPEECH
Kyu Jeong Han, Sriram Ganapathy, Ming Li, Mohamed Kamal Omar, Shrikanth S. Narayanan
2013 Misc conf
Unsupervised channel adaptation for language identification using co-training.
ICASSP
Sriram Ganapathy, Mohamed Kamal Omar, Jason W. Pelecanos
2012 Misc conf
Keyword-conditioned phone N-gram modeling with contextual information for speaker verification.
ICASSP
Kyu Jeong Han, Jason W. Pelecanos, Mohamed Kamal Omar
2012 — conf
Noisy channel adaptation in language identification.
SLT
Sriram Ganapathy, Mohamed Kamal Omar, Jason W. Pelecanos
2012 A conf
On the Use of Non-Linear Polynomial Kernel SVMs in Language Recognition.
INTERSPEECH
Sibel Yaman, Jason W. Pelecanos, Mohamed Kamal Omar
2011 A conf
Boosting Speaker Recognition Performance with Compact Representations.
INTERSPEECH
Sibel Yaman, Jason W. Pelecanos, Mohamed Kamal Omar
2011 A conf
Conversational-Side-Specific Inter-Session Variability Compensation.
INTERSPEECH
Mohamed Kamal Omar, Jason W. Pelecanos
2011 Misc conf
Feature normalization for speaker verification in room reverberation.
ICASSP
Sriram Ganapathy, Jason W. Pelecanos, Mohamed Kamal Omar
2011 Misc conf
Forensically inspired approaches to automatic speaker recognition.
ICASSP
Kyu Jeong Han, Mohamed Kamal Omar, Jason W. Pelecanos, Cezar Pendus, Sibel Yaman, Weizhong Zhu
2010 Misc conf
A novel approach to detecting non-native speakers and their native language.
ICASSP
Mohamed Kamal Omar, Jason W. Pelecanos
2010 — conf
Training Universal Background Models for Speaker Recognition.
Odyssey
Mohamed Kamal Omar, Jason W. Pelecanos
2009 Misc conf
Maximum margin linear kernel optimization for speaker verification.
ICASSP
Mohamed Kamal Omar, Jason W. Pelecanos, Ganesh N. Ramaswamy
2007 A conf
A variational approach to robust maximum likelihood estimation for speech recognition.
INTERSPEECH
Mohamed Kamal Omar
2007 A conf
Regularized feature-based maximum likelihood linear regression for speech recognition.
INTERSPEECH
Mohamed Kamal Omar
2006 — conf
Maximum Conditional Mutual Information Weighted Scoring for Speech Recognition.
ICASSP (1)
Mohamed Kamal Omar, Ganesh N. Ramaswamy
2005 A conf
Adaptive speech analytics: system, infrastructure, and behavior.
INTERSPEECH
Upendra V. Chaudhari, Ganesh N. Ramaswamy, Edward A. Epstein, Sasha Caskey, Mohamed Kamal Omar
2005 — conf
Blind Change Detection for Audio Segmentation.
ICASSP (1)
Mohamed Kamal Omar, Upendra V. Chaudhari, Ganesh N. Ramaswamy
2005 A conf
Maximum conditional mutual information modeling for speaker verification.
INTERSPEECH
Mohamed Kamal Omar, Jirí Navrátil, Ganesh N. Ramaswamy
2004 J jnl
Model enforcement: a unified feature transformation framework for classification and recognition.
IEEE Trans. Signal Process.
Mohamed Kamal Omar, Mark Hasegawa-Johnson
2003 — —
Acoustic Feature Design for Speech Recognition, a Statistical Information-Theoretic Approach
Mohamed Kamal Omar
2003 J jnl
Approximately independent factors of speech using nonlinear symplectic transformation.
IEEE Trans. Speech Audio Process.
Mohamed Kamal Omar, Mark Hasegawa-Johnson
2003 A conf
Maximum conditional mutual information projection for speech recognition.
INTERSPEECH
Mohamed Kamal Omar, Mark Hasegawa-Johnson
2003 A conf
Non-linear maximum likelihood feature transformation for speech recognition.
INTERSPEECH
Mohamed Kamal Omar, Mark Hasegawa-Johnson
2002 A conf
An evaluation of using mutual information for selection of acoustic-features representation of phonemes for speech recognition.
INTERSPEECH
Mohamed Kamal Omar, Ken Chen, Mark Hasegawa-Johnson, Yigal Brandman
2002 Misc conf
Maximum mutual information based acoustic-features representation of phonological features for speech recognition.
ICASSP
Mohamed Kamal Omar, Mark Hasegawa-Johnson