Mohamed Afify

74 papers A 15B 1Misc 11Journal 26Unranked 21
YearRankTypeTitle / Venue / Authors
2025 J jnl
Privacy-Preserving Transformers: SwiftKey's Differential Privacy Implementation.
CoRR
Abdelrahman Abouelenin, Mohamed Abdelrehim, Raffy Fahim, Amr Hendy, Mohamed Afify
2024 J jnl
On-Device Emoji Classifier Trained with GPT-based Data Augmentation for a Mobile Keyboard.
CoRR
Hossam Amer, Joe Osborne, Michael Zaki, Mohamed Afify
2024 J jnl
Simply Trainable Nearest Neighbour Machine Translation with GPU Inference.
CoRR
Hossam Amer, Abdelrahman Abouelenin, Mohamed Maher, Evram Nairouz, Mohamed Afify, Hany Awadalla
2023 J jnl
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation.
CoRR
Amr Hendy, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, Hany Hassan Awadalla
2022 J jnl
A Robust Intelligent System for Detecting Tomato Crop Diseases Using Deep Learning.
Int. J. Softw. Sci. Comput. Intell.
Mohamed Afify, Mohamed Loey, Ahmed El-Sawy
2022 — conf
Domain Specific Sub-network for Multi-Domain Neural Machine Translation.
AACL/IJCNLP (2)
Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Y. Tawfik
2022 J jnl
Domain Specific Sub-network for Multi-Domain Neural Machine Translation.
CoRR
Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Y. Tawfik
2022 Misc conf
Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU.
AMTA
Hossam Amer, Mohamed Afify, Young Jin Kim, Hitokazu Matsushita, Hany Hassan
2022 J jnl
Fast Vocabulary Projection Method via Clustering for Multilingual Machine Translation on GPU.
CoRR
Hossam Amer, Young Jin Kim, Mohamed Afify, Hitokazu Matsushita, Hany Hassan Awadalla
2022 J jnl
Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation.
CoRR
Muhammad N. ElNokrashy, Amr Hendy, Mohamed Maher, Mohamed Afify, Hany Hassan Awadalla
2022 Misc conf
Language Tokens: Simply Improving Zero-Shot Multi-Aligned Translation in Encoder-Decoder Models.
AMTA
Muhammad N. ElNokrashy, Amr Hendy, Mohamed Maher, Mohamed Afify, Hany Hassan
2021 J jnl
Connecting Arabs: bridging the gap in dialectal speech recognition.
Commun. ACM
Ahmed Ali, Shammur A. Chowdhury, Mohamed Afify, Wassim El-Hajj, Hazem M. Hajj, Mourad Abbas, Amir Hussein, Nada Ghneim, Mohammad A. M. Abushariah, Assal A. M. Alqudah
2021 — conf
Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs.
WMT@EMNLP
Amr Hendy, Esraa A. Gad, Mohamed Abdelghaffar, Jailan S. ElMosalami, Mohamed Afify, Ahmed Y. Tawfik, Hany Hassan Awadalla
2021 J jnl
Ensembling of Distilled Models from Multi-task Teachers for Constrained Resource Language Pairs.
CoRR
Amr Hendy, Esraa A. Gad, Mohamed Abdelghaffar, Jailan S. ElMosalami, Mohamed Afify, Ahmed Y. Tawfik, Hany Hassan Awadalla
2020 J jnl
Deep Learning in Plant Diseases Detection for Agricultural Crops: A Survey.
Int. J. Serv. Sci. Manag. Eng. Technol.
Mohamed Loey, Ahmed El-Sawy, Mohamed Afify
2020 — conf
Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions.
WMT@EMNLP
Muhammad N. ElNokrashy, Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Y. Tawfik, Hany Hassan Awadalla
2020 J jnl
Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions.
CoRR
Muhammad N. ElNokrashy, Amr Hendy, Mohamed Abdelghaffar, Mohamed Afify, Ahmed Y. Tawfik, Hany Hassan Awadalla
2019 — conf
Cloud-Based IoT Smart Parking System for Minimum Parking Delays on Campus.
ICIOT
Nesreen Alsbou, Mohamed Afify, Imad Ali
2019 — conf
Smart IoT In-Car Life Detector System to Prevent Car Deaths.
ICIOT
Nesreen Alsbou, Ka Hei Samuel Chen, Mohamed Afify
2018 — conf
3D smart mobile platform design for modeling motion artifacts in CT imaging of cancer patients.
I2MTC
Nesreen Alsbou, Mohamed Afify, Kushal Thapa, Imad Ali
2018 — conf
Smart engine speed control system with ECU system interface.
I2MTC
Mohamed Afify, Alaeddin S. A. Abuabed, Nesreen Alsbou
2018 — conf
Text-Independent Speaker Verification Based on Deep Neural Networks and Segmental Dynamic Time Warping.
SLT
Mohamed Adel, Mohamed Afify, Akram Gaballah, Magda B. Fayek
2018 J jnl
Text-Independent Speaker Verification Based on Deep Neural Networks and Segmental Dynamic Time Warping.
CoRR
Mohamed Adel, Mohamed Afify, Akram Gaballah
2013 A conf
Language-independent call routing using the large margin estimation principle.
INTERSPEECH
Moataz El Ayadi, Mohamed Afify
2013 J jnl
Stereo hidden Markov modeling for noise robust speech recognition.
Comput. Speech Lang.
Xiaodong Cui, Mohamed Afify, Yuqing Gao, Bowen Zhou
2012 A conf
Sparse Bayesian Factor Analysis for Stereo-based Stochastic Mapping.
INTERSPEECH
Xiaodong Cui, Mohamed Afify, George Saon, Vaibhava Goel
2012 Misc conf
Stereo-based stochastic mapping with context using probabilistic PCA for noise robust automatic speech recognition.
ICASSP
Xiaodong Cui, Mohamed Afify, Bowen Zhou
2010 Misc conf
Continuous space language modeling techniques.
ICASSP
Ruhi Sarikaya, Ahmad Emami, Mohamed Afify, Bhuvana Ramabhadran
2009 J jnl
Stereo-Based Stochastic Mapping for Robust Speech Recognition.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Xiaodong Cui, Yuqing Gao
2009 Misc conf
Stereo-based stochastic mapping with discriminative training for noise robust speech recognition.
ICASSP
Xiaodong Cui, Mohamed Afify, Yuqing Gao
2009 — conf
Tied-Mixture Language Modeling in Continuous Space.
HLT-NAACL
Ruhi Sarikaya, Mohamed Afify, Brian Kingsbury
2008 J jnl
Joint Morphological-Lexical Language Modeling for Processing Morphologically Rich Languages With Application to Dialectal Arabic.
IEEE Trans. Speech Audio Process.
Ruhi Sarikaya, Mohamed Afify, Yonggang Deng, Hakan Erdogan, Yuqing Gao
2008 Misc conf
MMSE-based stereo feature stochastic mapping for noise robust speech recognition.
ICASSP
Xiaodong Cui, Mohamed Afify, Yuqing Gao
2008 A conf
Machine translation in continuous space.
INTERSPEECH
Ruhi Sarikaya, Yonggang Deng, Mohamed Afify, Brian Kingsbury, Yuqing Gao
2008 A conf
N-best based stochastic mapping on stereo HMM for noise robust speech recognition.
INTERSPEECH
Xiaodong Cui, Mohamed Afify, Yuqing Gao
2007 J jnl
Comments on Vocal Tract Length Normalization Equals Linear Transformation in Cepstral Space.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Olivier Siohan
2007 — conf
Gaussian Mixture Language Models for Speech Recognition.
ICASSP (4)
Mohamed Afify, Olivier Siohan, Ruhi Sarikaya
2007 — conf
Joint Morphological-Lexical Language Modeling (JMLLM) for Arabic.
ICASSP (4)
Ruhi Sarikaya, Mohamed Afify, Yuqing Gao
2007 J jnl
Statistical Analysis of Minimum Classification Error Learning for Gaussian and Hidden Markov Model Classifiers.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Xinwei Li, Hui Jiang
2007 — conf
Stereo-Based Stochastic Mapping for Robust Speech Recognition.
ICASSP (4)
Mohamed Afify, Xiaodong Cui, Yuqing Gao
2007 — conf
The Impact of ASR on Speech-to-Speech Translation Performance.
ICASSP (4)
Ruhi Sarikaya, Bowen Zhou, Daniel Povey, Mohamed Afify, Yuqing Gao
2006 — conf
IBM Mastor: Multilingual Automatic Speech-To-Speech Translator.
ICASSP (5)
Yuqing Gao, Bowen Zhou, Liang Gu, Ruhi Sarikaya, Hong-Kwang Kuo, Antti-Veikko I. Rosti, Mohamed Afify, Weizhong Zhu
2006 A conf
On the use of morphological analysis for dialectal Arabic speech recognition.
INTERSPEECH
Mohamed Afify, Ruhi Sarikaya, Hong-Kwang Jeff Kuo, Laurent Besacier, Yuqing Gao
2005 J jnl
A new verification-based fast-match for large vocabulary continuous speech recognition.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Feng Liu, Hui Jiang, Olivier Siohan
2005 J jnl
Accurate compensation in the log-spectral domain for noisy speech recognition.
IEEE Trans. Speech Audio Process.
Mohamed Afify
2005 A conf
Extended baum-welch reestimation of Gaussian mixture models based on reverse Jensen inequality.
INTERSPEECH
Mohamed Afify
2005 A conf
Recent progress in Arabic broadcast news transcription at BBN.
INTERSPEECH
Mohamed Afify, Long Nguyen, Bing Xiang, Sherif M. Abdou, John Makhoul
2005 — conf
Statistical Performance Analysis of MCE/GPD Learning in Gaussian Classifiers and Hidden Markov Models.
ICASSP (1)
Mohamed Afify, Xinwei Li, Hui Jiang
2005 A conf
The BBN RT04 English broadcast news transcription system.
INTERSPEECH
Long Nguyen, Bing Xiang, Mohamed Afify, Sherif M. Abdou, Spyros Matsoukas, Richard M. Schwartz, John Makhoul
2004 B conf
Collection and Evaluation of Broadcast News Data for Arabic.
LREC
Mohamed Afify, Ossama Emam
2004 J jnl
Sequential estimation with optimal forgetting for robust speech recognition.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Olivier Siohan
2003 A conf
An accurate noise compensation algorithm in the log-spectral domain for robust speech recognition.
INTERSPEECH
Mohamed Afify
2002 Misc conf
A discriminative training criterion and an associated EM learning algorithm.
ICASSP
Mohamed Afify, Olivier Siohan
2002 J jnl
Upper and lower bounds on the mean of noisy speech: application to minimax classification.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Olivier Siohan, Chin-Hui Lee
2001 A conf
A new verification-based fast match approach to large vocabulary speech recognition.
INTERSPEECH
Feng Liu, Mohamed Afify, Hui Jiang, Olivier Siohan
2001 A conf
A real-time Japanese broadcast news closed-captioning system.
INTERSPEECH
Olivier Siohan, Akio Ando, Mohamed Afify, Hui Jiang, Chin-Hui Lee, Qi Li, Feng Liu, Kazuo Onoe, Frank K. Soong, Qiru Zhou
2001 A conf
Evaluating the Aurora connected digit recognition task - a bell labs approach.
INTERSPEECH
Mohamed Afify, Hui Jiang, Filipp Korkmazskiy, Chin-Hui Lee, Qi Li, Olivier Siohan, Frank K. Soong, Arun C. Surendran
2001 A conf
Minimax classification with parametric neighborhoods for noisy speech recognition.
INTERSPEECH
Mohamed Afify, Olivier Siohan, Chin-Hui Lee
2001 A conf
OASIS natural language call steering trial.
INTERSPEECH
Peter J. Durston, Mark Farrell, David Attwater, James Allen, Hong-Kwang Jeff Kuo, Mohamed Afify, Eric Fosler-Lussier, Chin-Hui Lee
2001 Misc conf
Quantitative method for modeling context in concatenative synthesis using large speech database.
ICASSP
Wael Hamza, Mohsen A. Rashwan, Mohamed Afify
2001 Misc conf
Sequential noise estimation with optimal forgetting for robust speech recognition.
ICASSP
Mohamed Afify, Olivier Siohan
2000 A conf
Constrained maximum likelihood linear regression for speaker adaptation.
INTERSPEECH
Mohamed Afify, Olivier Siohan
1999 J jnl
A minimum cross-entropy approach to hidden Markov model adaptation.
IEEE Signal Process. Lett.
Mohamed Afify, Yifan Gong, Jean-Paul Haton
1999 — conf
Phoneme recognition system based on HMM with distributed VQ codebook.
EUROSPEECH
Mohamed Debyeche, Mohamed Afify, Jean Paul Haton
1999 — conf
Sequential bias compensation for robust speech recognition.
EUROSPEECH
Mohamed Afify
1998 J jnl
A general joint additive and convolutive bias compensation approach applied to noisy Lombard speech recognition.
IEEE Trans. Speech Audio Process.
Mohamed Afify, Yifan Gong, Jean Paul Haton
1998 J jnl
Environment normalization training and environment adaptation using mixture stochastic trajectory model.
Speech Commun.
Irina Illina, Mohamed Afify, Yifan Gong
1998 Misc conf
Minimum cross-entropy adaptation of hidden Markov models.
ICASSP
Mohamed Afify, Jean-Paul Haton
1997 Misc conf
A unified maximum likelihood approach to acoustic mismatch compensation: application to noisy Lombard speech recognition.
ICASSP
Mohamed Afify, Yifan Gong, Jean-Paul Haton
1997 — conf
An acoustic subword unit approach to non-linguistic speech feature identification.
EUROSPEECH
Mohamed Afify, Yifan Gong, Jean Paul Haton
1997 — conf
Correlation based predictive adaptation of hidden Markov models.
EUROSPEECH
Mohamed Afify, Yifan Gong, Jean Paul Haton
1996 J jnl
Estimation of mixtures of stochastic dynamic trajectories: application to continuous speech recognition.
Comput. Speech Lang.
Mohamed Afify, Yifan Gong, Jean Paul Haton
1995 — conf
Stochastic trajectory models for speech recognition: an extension to modelling time correlation.
EUROSPEECH
Mohamed Afify, Yifan Gong, Jean Paul Haton
1994 — conf
Nonlinear time alignment in stochastic trajectory models for speech recognition.
ICSLP
Mohamed Afify, Yifan Gong, Jean Paul Haton