A1055
Title: Enhancing sign language translation with real-time AI technology
Authors: Elisa Cabana Garceran del Vall - CUNEF, SL (Spain) [presenting]
Abstract: A primary challenge for the deaf and hearing-impaired community stems from the communication gap with the hearing society, which can greatly impact their daily lives and result in social exclusion. To foster inclusivity in society, the endeavor focuses on developing a cost-effective, resource-efficient, and open technology based on artificial intelligence designed to assist people in learning and using sign language for communication. Specifically, the aim is to create a computer vision system for American sign language (ASL) fingerspelling classification in real time that can serve as a learning application. For this purpose, an extensive dataset of images of ASL alphabet signs has been compiled. Several neural network classification models are compared and implemented into the final real-time system with the overall best performance metrics. Valuable insights for the sign language translation scenario and significant advances in ongoing academic research are provided.
