M
Mohamed Afify
Researcher at Cairo University
Publications - 57
Citations - 855
Mohamed Afify is an academic researcher from Cairo University. The author has contributed to research in topics: Speech processing & Hidden Markov model. The author has an hindex of 16, co-authored 49 publications receiving 774 citations. Previous affiliations of Mohamed Afify include IBM & Bell Labs.
Papers
More filters
Proceedings Article
On the Use of Morphological Analysis for Dialectal Arabic Speech Recognition
TL;DR: A simple word decomposition algorithm is introduced which only requires a text corpus and a predefined list of affixes to create the lexicon for Iraqi Arabic ASR and results in about 10% relative improvement in word error rate (WER).
Proceedings ArticleDOI
IBM MASTOR SYSTEM: Multilingual Automatic Speech-to-Speech Translator
Yuqing Gao,Bowen Zhou,Ruhi Sarikaya,Mohamed Afify,Hong-Kwang Kuo,Weizhong Zhu,Yonggang Deng,Charles Prosser,Wei Zhang,Laurent Besacier +9 more
TL;DR: The IBM MASTOR is described, a speech-to-speech translation system that can translate spontaneous free-form speech in real-time on both laptop and hand-held PDAs and can handle two language pairs (including a low-resource language).
Proceedings ArticleDOI
Stereo-Based Stochastic Mapping for Robust Speech Recognition
TL;DR: A stochastic mapping technique for robust speech recognition that uses stereo data based on constructing a Gaussian mixture model for the joint distribution of the clean and noisy features and using this distribution to predict the clean speech during testing.
Journal ArticleDOI
How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation
Amr Hendy,Mohamed Gomaa Abdelrehim,Amr Sharaf,Vikas Raunak,Mohamed Gabr,Hitokazu Matsushita,Young-Jin Kim,Mohamed Afify,Hany Hassan Awadalla +8 more
TL;DR: The authors presented a comprehensive evaluation of pre-trained transformer models for machine translation, covering various aspects such as quality of different GPT models in comparison with state-of-the-art research and commercial systems, effect of prompting strategies, robustness towards domain shifts and document-level translation.
Proceedings ArticleDOI
Recent progress in Arabic broadcast news transcription at BBN.
TL;DR: It is demonstrated that switching to phonetic models is capable of reducing the word error rate by up to 14% relative, for different test sets, compared to the traditional grapheme based approach.