The Transaura team consists of three Universitas Indonesia (UI) students, namely Daffa Fairuzaufa Athallah Raharjo (Faculty of Engineering UI, 2020), Aine Shahnaz Tjandraatmadja (Faculty of Nursing UI, 2020), and Almaz Scarletta Tjakrashafanti (Faculty of Humanities UI, 2018) created the “TRANSAURA” sign language translation tool using TensorFlow and Raspberry Pi technology.
They took a keen interest in sign language because they realized the lack of accessibility of sign language interpretation for the general public. “This raises social issues for people with disabilities, such as educational disparities, inequality of employment opportunities, and inclusion of social participation.
The Transaura team under the guidance of Dodi Sudiana, lecturer at the Department of Electrical Engineering, Faculty of Engineering UI (FEUI), won third place at the national research grant competition, Tanoto Student Research Awards 2021, in the field of appropriate technology. The team conducted research and underwent gradual selection from the university level to the national level from June 2021 to January 2022.
In the competition, the Transaura Team competed with 24 other teams. The Dean of FEUI, Prof. Dr. Heri Hermansyah, ST., M.Eng., IPU, hopes that this research can be continued to develop a more friendly environment for people with disabilities in Indonesia.
“Many deaf friends who graduated from Sekolah Luar Biasa (Extraordinary Schools, Indonesian educational institutions for children with special needs) experience difficulties in the job search process as well as difficulties in accessing various public facilities. Our goal in developing Transaura is to make it easier for our deaf friends to have two-way communication. Transaura’s design is a portable box that can be placed anywhere. It has two sides, one for deaf friends and the other for hearing friends,” says Daffa, the originator of the Transaura idea.
“Two screens at the front and rear allow for two-way communication. The first screen will house the sign language translator using object detection with the help of TensorFlow. The second screen will output text located on the back side of the device. The main component that is the brain of Transaura is the Raspberry Pi microprocessor,” Almaz explained regarding Transaura components.
TensorFlow is an open source library for large-scale numerical computing and machine learning. TensorFlow can train and run deep neural networks for handwritten digit classification, image recognition, word embedding, recurrent neural networks, sequence-to-sequence models for machine translation, natural language processing, and PDE (partial differential equation) based simulations. Interestingly, TensorFlow supports large-scale production prediction with the same model that can be used for training.
Transaura is made to be used in office areas, supermarkets and transportation facilities. “With Transaura, we hope to create equality for people with disabilities in various jobs, as the name Transaura (translating aura) suggests. Opportunities and equality for people with disabilities are the foundation of this research,” says Transaura team leader Aine.
Author: Tikka Anggraeni | Editor: Mariana Sumanti
