Publication year: 2023
ISBN: CCE00085
Internet Resource: Please Login to download book
Our project aims to aid deaf-mute people by tracking hand movements of the deaf-mute person for word level American Sign Language using WLASL model that include 2D CNN -3D CNN and RNN networks training on WLASL large video dataset, then generating the corresponding text and analyzing the person's facial gestures to generate information related to the tone of voice that is most appropriate to the person's age, gender, and race through MTCNN network algorithm that training on generated dataset by us depending on blending VOXCELEB dataset and VGGFACE dataset .
Subject: Computer sceince, Sign language detection, Face encoder, Text to speech, Face to voice, Voxceleb