Sign language recognition and text-to-speech translation

Palla, Vineeth (2023) Sign language recognition and text-to-speech translation. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (828kB) | Preview

Abstract

Sign language recognition and text-to-speech translation technologies have emerged as revolutionary tools for improving communication accessibility for those who are deaf or hard of hearing. This study employs deep learning models, notably Convolutional Neural Networks (CNNs), to create a robust system capable of identifying and interpreting a wide range of sign language movements into spoken English. The study compares the performance of three different CNN models, namely CNN with Adam, CNN with SGD, and CNN with RMSProp, in terms of accuracy, precision, recall, and F1-score. Among these models, CNN with RMSProp performed exceptionally well, with a score of 0.9996. The recognition capabilities of this model offers great potential for real-time translation and communication. The study also looks at how recognition algorithms adapt to different sign language dialects, how they perform in uncontrolled contexts, and how they may be customised to meet the demands of different users. The proposed technology is set to overcome communication barriers and contribute to a more inclusive society by providing a realistic solution for those who are deaf or hard of hearing.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Syed, Muslim Jameel UNSPECIFIED
Uncontrolled Keywords:	Sign language recognition; Text-to-speech translation; Convolutional Neural Networks (CNN); Deep learning
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence P Language and Literature > P Philology. Linguistics > Semiotics > Language. Linguistic theory > Gesture. Sign language
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Tamara Malone
Date Deposited:	04 Apr 2025 16:31
Last Modified:	04 Apr 2025 16:31
URI:	https://norma.ncirl.ie/id/eprint/7372

Actions (login required)

View Item