Master-ASL: Sign Language Learning and Assessment System

According to the World Health Organization (WHO), over 5% of the world’s population have hearing impairments. Sign language plays a significant role in bridging the communication gap between people of muteness, persons with hearing loss and general public. Currently most sign language learning systems have a considerable deficiency in real time practice and evaluation. This research aims to develop a sign language learning mobile application, called Master-ASL, to support American sign language (ASL) education through learning and assessment processes. It uses machine learning and multimedia presentations to provide an easy, interactive, and portable learning environment. In brief, users can learn all the ASL alphabets and digits through multimedia presentations in the application. In addition, different types of assessments are developed using the constructivist learning and game-oriented approaches. The game environment incorporates the concept of machine learning object recognition technology to engage users in matching ASL characters with corresponding pictures, and vice versa. The proposed framework is successfully implemented on smart phone platform and is demonstrated through user studies to help keep users motivated to learn more by performing tasks to construct their knowledge.