I'm a Computer Science researcher specializing in Arabic Language Processing and Computer Vision at Chalmers University of Technology. My research focuses on developing innovative solutions for Arabic sign language recognition, speech processing, and multimodal learning.
I have contributed to several groundbreaking projects, including the development of the RGB Arabic Alphabet Sign Language (AASL) dataset and the Massive Arabic Speech Corpus (MASC). My recent work on AraCLIP introduces a novel approach to Arabic image retrieval using cross-lingual learning and knowledge distillation techniques.
My research interests span across multiple areas including sign language recognition, speech processing, and vision-language models with a particular focus on Arabic language applications. I am passionate about bridging the gap between deep learning technologies and Arabic language processing, working to create more inclusive and effective solutions for Arabic-speaking communities. Currently, I'm exploring new approaches in cross-modal learning and developing robust models for Arabic language understanding in visual contexts.
Mohammad Al-Fetyani, Muhammad Al-Barham, Gheith A. Abandah, A. Alsharkawi, Maha Dawas
Spoken Language Technology Workshop 2023
Muhammad Al-Barham, Ahmad Abu Sa'Aleek, Mohammad Q. Al-Odat, G. Hamad, Musa S. Al-Yaman, A. Elnagar
International Conference on Information, Communications and Signal Processing 2022
Muhammad Al-Barham, Imad Afyouni, Khalid Almubarak, A. Elnagar, Ayad Turky, Ibrahim Hashem
ARABICNLP 2024