RNN-GAN Integration for Enhanced Voice-Based Email Accessibility: A Comparative Study for Visually Impaired Users

This paper presents the integration of Recurrent Neural Network-based GenerativeAdversarial Networks (RNN-GAN) into voice-enabled email access systems for personswith visual impairments. The other neural network architectures havebeen comparedincluding LSTM and GRU. The goal is to enhance spoken command comprehension,information extraction, and contextually relevant response generation. This study usesRNN-LSTM, RNN-GRU and compares with the proposed model (RNN-GAN). RNN-GANresults in higher word accuracy (approximately 70-95%), real-time processing, androbustness to change of speech as compared with the previous models. The challengesinvolved computational resources needs and the privacy implications. In the era of machinelearning, personalization seems to be a significant factor along with enhanced security,multilingual support and finally it has to make sure that model inference is optimised forthese low resource environments. This research work helps to make the email moreaccessible for visually impaired users and thus improve digital inclusion.