Arabic Automatic Speech Recognition
The research project focuses on the development of an improved automatic speech recognition (ASR) system for the Arabic language. Arabic is a complex and rich language with a wide range of dialects and a unique writing system, and current ASR systems for Arabic still have a number of limitations. We aim to use a machine learning-based approach, including techniques such as data augmentation and transfer learning, to train a deep neural network-based ASR model on a large dataset of spoken Arabic. The resulting system will be evaluated using standard metrics such as word error rate and character error rate and will be compared to state-of-the-art ASR systems for Arabic. The ultimate goal of this project is to contribute to the development of more accurate and reliable ASR systems for Arabic, with potential applications in fields such as education, assistive technology and digital accessibility solutions, as well as facilitating the transcription and translation of spoken Arabic.
Automatic Speech Recognition (ASR), also known as Speech-To-Text (STT) or computer speech recognition, has been an active field of research recently. This study aims to chart this field by performing a Systematic Literature Review (SLR) to give insight into the ASR studies proposed, especially for the Arabic language. The purpose is to highlight the trends of research about Arabic ASR and guide researchers with the most significant studies published over ten years from 2011 to 2021. This SLR attempts to tackle seven specific research questions related to the toolkits used for developing and evaluating Arabic ASR, the supported type of the Arabic language…
MDPI Applied Sciences | Special Issue: Automatic Speech Recognition | (Q2, Impact Factor 2020: 2.679) | 2022