Speak-to-Sign: A Real-Time NLP-Driven Framework for Indian Sign Language Translation: A Review

DOI

10.2991/978-94-6463-738-0_30How to use a DOI?

Keywords

Audio-to-Sign Language Conversion; Indian Sign Language (ISL); Natural Language Processing (NLP); real-time processing; sign language visualization; gesture-based communication; accessibility solutions; inclusive technology; linguistic tokenization; multimodal interaction; assistive communication tools; dynamic gesture generation; hearing-impaired accessibility; Human-Computer Interaction (HCI); scalable assistive systems

Abstract

The primary impact of communication barriers on the lives of many deaf or hard-of-hearing individuals lies in their ability to understand and comprehend most spoken languages. Accordingly, this paper presents an effective system which can convert speech to Indian Sign Language (ISL) via images and gifs. The proposed system utilizes Python with Google’s Speech Recognizer API contact to convert speech to text and then applies NLP on the text to generate ISL tokens that are rendered as gestures for user-friendly access to the deaf. The major features include efficient speech-to-text conversion and NLP-driven accurate processing and gesture generation in ISL to augment the efficiency of existing solutions in translation, processing speed, and privacy issues. The system promotes flexibility via the most current algorithms and a modular design to be easily added features or modified in the future. It enhances access to education, employment, and social participation for the hearing impaired and proclaimed as a contribution toward a better society. This offers more than just an aid for communication systems; it promotes inclusivity and technology itself among innovations.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - S. Sudeshna
AU  - B. Sai Nikhitha
AU  - B. Vinaya
AU  - D. Dhanasree
AU  - D. Chandrika
PY  - 2025
DA  - 2025/06/22
TI  - Speak-to-Sign: A Real-Time NLP-Driven Framework for Indian Sign Language Translation: A Review
BT  - Proceedings of the International Conference on Advances and Applications in Artificial Intelligence (ICAAAI 2025)
PB  - Atlantis Press
SP  - 360
EP  - 377
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-738-0_30
DO  - 10.2991/978-94-6463-738-0_30
ID  - Sudeshna2025
ER  -