Interactive VBE and IPSL Aid for the Disabled using a GRU-based Model

In a world of billions communication becomes the radical thing that makes us human. Without communication, people are mere objects with a soul. Unfortunately, not all of us are blessed with being able to communicate freely. Interaction between the disabled and the ordinary poses a huge challenge. This paper proposes to solve this problem by developing a sign language identifier by combining machine learning and web development techniques to aid the needy. IPSL (Indo-Pakistani Sign Language) is one such language that is not represented as much as it should be. Despite being used actively by more than 15 Million people in the deaf community, IPSL is unknown to most of the world. IPSL will be made detectable with the proposed model that is combined with a VBE (Voice Based Email) system to aid not only the deaf but also the blind, using a GRU model for the same. GRU is already a well defined model, but this paper intends to show how this deep learning model can be used for IPSL, having never been done before, as it is usually done for the popular languages like ASL and BSL.