Mohamed Kamal Omar

According to our database, Mohamed Kamal Omar authored at least 29 papers between 2002 and 2016.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2016

A factor analysis model of sequences for language recognition.

Mohamed Kamal Omar

Proceedings of the 2016 IEEE Spoken Language Technology Workshop, 2016

2015

Fast approximate i-vector estimation using PCA.

Mohamed Kamal Omar

Proceedings of the 2015 IEEE International Conference on Acoustics, 2015

2014

Robust language identification using convolutional neural network features.

Sriram Ganapathy, Kyu Jeong Han, Samuel Thomas, Mohamed Kamal Omar, Maarten Van Segbroeck, Shrikanth S. Narayanan

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

Shift-invariant features for speech activity detection in adverse radio-frequency channel conditions.

Mohamed Kamal Omar, Sriram Ganapathy

Proceedings of the IEEE International Conference on Acoustics, 2014

2013

TRAP language identification system for RATS phase II evaluation.

Kyu Jeong Han, Sriram Ganapathy, Ming Li, Mohamed Kamal Omar, Shrikanth S. Narayanan

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Unsupervised channel adaptation for language identification using co-training.

Sriram Ganapathy, Mohamed Kamal Omar, Jason W. Pelecanos

Proceedings of the IEEE International Conference on Acoustics, 2013

2012

Noisy channel adaptation in language identification.

Sriram Ganapathy, Mohamed Kamal Omar, Jason W. Pelecanos

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

On the Use of Non-Linear Polynomial Kernel SVMs in Language Recognition.

Sibel Yaman, Jason W. Pelecanos, Mohamed Kamal Omar

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Keyword-conditioned phone N-gram modeling with contextual information for speaker verification.

Kyu Jeong Han, Jason W. Pelecanos, Mohamed Kamal Omar

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Boosting Speaker Recognition Performance with Compact Representations.

Sibel Yaman, Jason W. Pelecanos, Mohamed Kamal Omar

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Conversational-Side-Specific Inter-Session Variability Compensation.

Mohamed Kamal Omar, Jason W. Pelecanos

Proceedings of the 12th Annual Conference of the International Speech Communication Association, 2011

Forensically inspired approaches to automatic speaker recognition.

Kyu Jeong Han, Mohamed Kamal Omar, Jason W. Pelecanos, Cezar Pendus, Sibel Yaman, Weizhong Zhu

Proceedings of the IEEE International Conference on Acoustics, 2011

Feature normalization for speaker verification in room reverberation.

Sriram Ganapathy, Jason W. Pelecanos, Mohamed Kamal Omar

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Training Universal Background Models for Speaker Recognition.

Mohamed Kamal Omar, Jason W. Pelecanos

Proceedings of the Odyssey 2010: The Speaker and Language Recognition Workshop, Brno, Czech Republic, June 28, 2010

A novel approach to detecting non-native speakers and their native language.

Mohamed Kamal Omar, Jason W. Pelecanos

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Maximum margin linear kernel optimization for speaker verification.

Mohamed Kamal Omar, Jason W. Pelecanos, Ganesh N. Ramaswamy

Proceedings of the IEEE International Conference on Acoustics, 2009

2007

A variational approach to robust maximum likelihood estimation for speech recognition.

Mohamed Kamal Omar

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

Regularized feature-based maximum likelihood linear regression for speech recognition.

Mohamed Kamal Omar

Proceedings of the 8th Annual Conference of the International Speech Communication Association, 2007

2006

Maximum Conditional Mutual Information Weighted Scoring for Speech Recognition.

Mohamed Kamal Omar, Ganesh N. Ramaswamy

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

Maximum conditional mutual information modeling for speaker verification.

Mohamed Kamal Omar, Jirí Navrátil, Ganesh N. Ramaswamy

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Adaptive speech analytics: system, infrastructure, and behavior.

Upendra V. Chaudhari, Ganesh N. Ramaswamy, Edward A. Epstein, Sasha Caskey, Mohamed Kamal Omar

Proceedings of the 9th European Conference on Speech Communication and Technology, 2005

Blind Change Detection for Audio Segmentation.

Mohamed Kamal Omar, Upendra V. Chaudhari, Ganesh N. Ramaswamy

Proceedings of the 2005 IEEE International Conference on Acoustics, 2005

2004

Model enforcement: a unified feature transformation framework for classification and recognition.

Mohamed Kamal Omar, Mark Hasegawa-Johnson

IEEE Trans. Signal Process., 2004

2003

Acoustic Feature Design for Speech Recognition, a Statistical Information-Theoretic Approach

Mohamed Kamal Omar

PhD thesis, 2003

Approximately independent factors of speech using nonlinear symplectic transformation.

Mohamed Kamal Omar, Mark Hasegawa-Johnson

IEEE Trans. Speech Audio Process., 2003

Non-linear maximum likelihood feature transformation for speech recognition.

Mohamed Kamal Omar, Mark Hasegawa-Johnson

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

Maximum conditional mutual information projection for speech recognition.

Mohamed Kamal Omar, Mark Hasegawa-Johnson

Proceedings of the 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003, 2003

2002

An evaluation of using mutual information for selection of acoustic-features representation of phonemes for speech recognition.

Mohamed Kamal Omar, Ken Chen, Mark Hasegawa-Johnson, Yigal Brandman

Proceedings of the 7th International Conference on Spoken Language Processing, ICSLP2002, 2002

Maximum mutual information based acoustic-features representation of phonological features for speech recognition.

Mohamed Kamal Omar, Mark Hasegawa-Johnson

Proceedings of the IEEE International Conference on Acoustics, 2002