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, the used feature extraction/classification techniques, the type of speech recognition, the performance of Arabic ASR, the existing gaps facing researchers, along with some future research. Across five databases, 38 studies met our defined inclusion criteria. Our results showed different open-source toolkits to support Arabic speech recognition. The most prominent ones were KALDI, HTK, then CMU Sphinx toolkits. A total of 89.47% of the retained studies cover modern standard Arabic, whereas 26.32% of them were dedicated to different dialects of Arabic. MFCC and HMM were presented as the most used feature extraction and classification techniques, respectively: 63% of the papers were based on MFCC and 21% were based on HMM. The review also shows that the performance of Arabic ASR systems depends mainly on different criteria related to the availability of resources, the techniques used for acoustic modeling, and the used datasets.

Deaf and Hard of Hearing (DHH) individuals often encounter significant challenges in communication and accessing digital content, with Sign Language as their primary mode of communication. Traditional Sign Language interpretation services and existing accessibility measures may not always be readily available or effective. This study explores the acceptance of signing avatars, specifically the culturally adapted BuHamad avatar, among DHH individuals in Qatar. Semi-structured interviews with 40 DHH participants, representing 10% of the deaf population in Qatar, were conducted using the Technology Acceptance Model (TAM). Factors such as perceived usefulness, ease of use, attitude, and behavioral intention to use the BuHamad avatar were examined through descriptive statistics and thematic analysis of qualitative data. Findings reveal that while participants generally hold positive attitudes towards the signing avatar and its potential to enhance accessibility, they do not view it as a substitute for human interpreters. Key usability issues, including avatar movement and appearance, were identified. This study introduces the Technology Acceptance Model of Signing Avatars (TAMSA) and provides insights into factors influencing the acceptance of signing avatars in Qatar. These insights can guide developers and designers in creating more effective and user-friendly avatars for the DHH community in Qatar and the broader Gulf region.

This paper proposes the first large-scale and annotated Qatari sign language dataset for continuous sign language processing. This dataset focuses on phrases and sentences commonly used in healthcare settings and contains 6300 records of 900 sentences. The dataset collection process involves diverse participants, including both hearing-impaired individuals and sign interpreters, to capture variations in signing styles, speeds, and other linguistic nuances. The data collection setup integrates advanced technology, including true depth cameras, to comprehensively record signing movements from various angles. The collected dataset is rich in content, encompassing different signing variations and linguistic intricacies. The dataset is publicly available in IEEE Dataport. The paper also analyzes the data captured to understand the trends and patterns within the data. As the global population with hearing difficulties continues to grow, there is a pressing need for effective sign language recognition systems to bridge the communication gap between the deaf and non-deaf communities and the introduction of the JUMLA-QSL-22 dataset constitutes a significant stride toward addressing this imperative need.

In spite of the fastest growing of technologies of information and communication in the education and the development of very sophisticated environments to improve learning and education, there are a few tools dedicated to deaf education due to the difficulty to create content in sign language. In this context, we present in this paper an ICT environment we developed to aid deaf people improving their social integration and communication capabilities. Our environment is a specialized LCS that generates multimedia courses to teach and learn sign language. These courses can be used either by deaf pupils to learn (or e-learn) sign language or also by hearing people to be able to communicate with deaf people. This educational environment uses mainly a Web-based interpreter of sign language developed in our research laboratory and called Websign. It is a tool that permits to interpret automatically written texts in visual-gestured-spatial language using avatar technology.

According to the World Federation of Deaf [1], there are about 70 million deaf people who use sign language as their first language. Despite the fact that sign languages represent the main way of communication for the 1% of the world population, they are still used by a minority of hearing people. No one can ignore the obvious barrier of the communication between deaf and hearing people. In this context, our project contributes to improving the accessibility of the deaf. Indeed, this work is a contribution in a new field of sign language's recognition through EMG signals. This article presents the first step started by the research laboratory LaTICE (www.latice.rnu.tn) to evaluates the usage EMG electromyogram signals provided by the sensors of Myo armband, in order to facilitate the communication between hearing and deaf people, and therefore enrich the library of gestures recognized by this device. In this paper, we will be focusing on extracting characteristics of the raw electromyographic signals obtained from the Myo armband to classify some hand-shapes of the language's alphabet, based on a supervised automatic learning approach.