Sign Language Recognition and Text-to-Speech Translation

Thorat, Sumitra Sambhaji (2023) Sign Language Recognition and Text-to-Speech Translation. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Communication is the most important aspect while conveying messages. The ability to listen and speak plays an important role while communicating. There are people who have difficulty in listening or speaking. As humans use verbal language, conversing with specially-abled people become a challenge. Because of the mentioned reason these people use sign language to communicate and everyone is not familiar with sign language. The unfamiliarity with sign language becomes a barrier while communicating. This research will assist the people who are unable to speak and listen to converse with normal people by using sign language recognition and converting these in text or speech. This is implemented using American and Indian sign language to reduce language barrier. Convolution Neural Network (CNN) was used for Indian Sign Language (ISL) and American Sign Language (ASL). In both dataset Image Augmentation was performed and text to speech was converted using Google Text to Speech library from python. The ISL achieved the accuracy of 99% and the loss observed was 0.5. The accuracy of ASL was observed to be 96% and the loss was 0.11.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Staikopoulos, Athanasios UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing P Language and Literature > P Philology. Linguistics > Semiotics > Language. Linguistic theory > Gesture. Sign language
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	27 May 2023 11:21
Last Modified:	27 May 2023 11:21
URI:	https://norma.ncirl.ie/id/eprint/6677

Actions (login required)

View Item