AAVAZ
Breaking Barriers Enabling Voices- Real time synthetic speech generation based on speaker lip movement.
Toward Scalable Sign Generation
A contextually appropriate fluid sign language generation through a co-articulated gloss-to-sign dictionary and diffusion-based interpolation.
Sign Language Question Answering
A scalable framework for enabling users with hearing impairment to ask and receive answers in sign language.
StethoSpeech
Speech generation through a clinical stethoscope attached to the skin.
LipMOOC
A modular synthetic massive open online course (MOOC), designed to teach lipreading using state-of-the-art AI generated face videos.
AI Assistant for the Visually Impaired
A handsfree, voice based low latency system that enables visually impaired individuals to ask questions about their current environment and provides back contextually aware answers in the form of audio.
Audiobook
A audio book platform built to cater to visually impaired readers, with platform book to audio generation as well as multi-lingual support.
Schooling Landscape for Children with Intellectual and Developmental Disabilities
A platform that aims to inform, connect and empower the families of individuals with intellectual and developmental disabilities.
Exo-Suit Sustainable
Exo-Suit Sustainable, smart, light-weight, customizable, lower body wearable exoskeleton for rehabilitation movements with safety protocols
Speech Technology Applications
Building a suite of speech models for tasks such as Speech-to-Speech translation, Prosody incorporated Text-to-Speech to enable enhanced language learning, as well as automated detection of speech disorders.
Ucchar e-Sudharak
An automatic english pronunciation corrector for school going children with a teacher in the loop.
Vyakaran e-Shikshak
Vyakaran e-Shikshak An automatic evaluator for English grammar in oral communication.
