What is it about?
This research focuses on developing a software system to bridge the communication gap between the Deaf and hearing communities in India. The goal is to create an application that converts spoken language into Indian Sign Language (ISL). The process involves two main steps: first, converting spoken words into text using voice-to-text technology; second, transforming this text into sign language by analyzing its grammar using natural language processing (NLP). The system synchronizes hand movements, posture, and body language to accurately represent ISL grammar. This user-friendly online application can be used on mobile devices and integrated into public spaces across India, making communication with Deaf individuals easier in both personal and professional settings.
Featured Image
Why is it important?
The application is vital as it addresses the communication barrier between Deaf and hearing individuals, promoting inclusivity and accessibility. By translating spoken language into Indian Sign Language (ISL) in real-time, it empowers Deaf individuals to interact seamlessly in both personal and professional settings. The integration of natural language processing to accurately reflect ISL grammar, ensuring culturally and linguistically appropriate communication makes this application very unique. Additionally, its mobile and public-space integration potential makes it a versatile tool that can significantly enhance communication for millions of Deaf individuals across India.
Perspectives
The challenges of understanding sign language and the conversion between spoken and sign language was very engaging and pushed me to explore new technologies and innovative solutions. Each step of the process, from understanding the nuances of ISL grammar to integrating natural language processing, has been both challenging and rewarding
Jeremiah Nunes
SRM University
Read the Original
This page is a summary of: Converting voice signal to visual Indian sign language (ISL), January 2024, American Institute of Physics,
DOI: 10.1063/5.0217832.
You can read the full text:
Contributors
The following have contributed to this page