Proposal Number: 5283
Domain: Information & Communication Technology
Theme(s): Multimodal, Multilingual and Cross-lingual Interfaces
Supporting Central Government Agency:
Budget (Rs. Lakhs): 376.80
Principal Investigator: Dr. K. Sreenivasa Rao
Principal Investigator Institute: Indian Institute of Technology Kharagpur
Co-Investigators:
Dr. S. R. M. Prasanna ,Indian Institute of Technology Guwahati
Dr. Priyankoo Sarmah ,Indian Institute of Technology Guwahati
Dr. Shrivastava Abhishek ,Indian Institute of Technology Guwahati
Dr. M. Sabarimalai Manikandan ,Indian Institute of Technology Bhubaneswar
Dr. K. Sri Rama Murty ,Indian Institute of Technology Hyderabad
Dr. Pabitra Mitra ,Indian Institute of Technology Kharagpur
Domain: Information & Communication Technology
Project Title
Development of Speech Interface for Form-filling application in Five Indian languages
Project Images
Image Caption:Overall flow diagram of the proposed form-filling system
Web Abstract
This project is aimed at developing and deploying speech interface for form-filling application (SiFA), which replaces the traditional keyboard for entering the responses. The proposed system interacts with the user in his/her mother tongue, in order to fill the responses. The SiFA system prompts the user with queries generated using a text-to-speech synthesis system, recognizes the user responses using an ASR system, and fills the form. We propose to develop modular framework for filling different fields in the forms, like name, address, date of birth etc., each of which may in turn involve several subfields, so that it can be easily deployed across the domains including, but not limited to, healthcare, education, governance, banking, etc. Since the proposed system is based purely on speech communication, it can help in taking the fruits of modern digitization techniques to the rural public, as well as the visually challenged population. The proposed system will be demonstrated in five different Indian languages, viz., Assamese, Bengali, Hindi, Odia and Telugu, as proof of the concept, and can be extended to other languages as well.