Mostafa Jebbar

About

Mostafa Jebbar is a researcher focused on advancing speech recognition technologies, particularly for under-resourced languages and dialects. His key research areas include deep learning-based speech processing, dialectal Arabic recognition, and human-machine interaction. Jebbar’s major contribution lies in developing and deploying machine learning models for Moroccan Arabic (“Darija”), a dialect often overlooked in mainstream speech systems. His most-cited work, “Moroccan's Arabic Speech Training And Deploying Machine Learning Models with Teachable Machine” (2022, 7 citations), demonstrates a practical approach to building accessible speech recognition tools using user-friendly platforms. In a related study, “Simulation of Car Driving by Voice Commands based on a Deep-Learning Model” (2022, 3 citations), he innovatively applies dialectal speech recognition to control robotic systems, simulating voice-driven car navigation. These works highlight Jebbar’s commitment to bridging the gap between cutting-edge AI and real-world applications for diverse linguistic communities. His research not only advances technical methodologies but also promotes inclusivity in speech technology, making it more adaptable to regional languages. For students and researchers, Jebbar’s work offers a compelling example of how deep learning can be tailored to solve practical problems in low-resource language settings.

Research Focus

Key Achievements

Top Papers

1. 1
   Moroccan's Arabic Speech Training And Deploying Machine Learning Models with Teachable Machine

   7 citations · 2022
2. 2
   Simulation of Car Driving by Voice Commands based on a Deep-Learning Model

   3 citations · 2022

Key Collaborators

Contact & Links