Guwahati: In a major scientific advancement with potential real-world impact, researchers at the Indian Institute of Technology (IIT) Guwahati have developed a novel underwater vibration sensor that can enable people with voice disabilities to communicate without using sound.
The innovation, created in collaboration with Ohio State University, USA, offers a promising solution for individuals who are unable to use conventional voice recognition systems due to vocal cord damage or speech disorders.
According to a statement issued by IIT-Guwahati on Monday, the new system detects subtle airflow patterns generated during the act of attempting to speak—specifically, the exhaled breath that causes minute waves on a water surface.
The sensor, positioned just below the air-water interface, captures these disturbances and translates them into electrical signals.
Made from a conductive and chemically reactive porous sponge, the sensor enables contactless, sound-free communication.
These signals are then processed using Convolutional Neural Networks (CNN), a form of artificial intelligence that allows the system to accurately interpret the intended speech patterns.
“This is one of the rare material designs that allows voice recognition by monitoring water waves caused by exhaled breath,” said Professor Uttam Manna, a lead member of the research team.
“It offers a viable alternative for individuals with partially or completely impaired vocal cords.”
Voice recognition has become a common feature in daily life, powering smart home devices, smartphones, and more.
However, it remains inaccessible to those who cannot produce audible sound.
The IIT-Guwahati innovation aims to bridge this gap through a unique combination of material science and AI.
ALSO READ: Smoking increases risk of slipped disc, say NEIGRIHMS doctors
Currently, a lab-scale prototype costs around Rs. 3,000, but researchers believe that with industry collaboration, the technology can be scaled and made more affordable for real-world applications.
Key features of the system include AI-driven signal processing, hands-free smart device control, and compatibility with voice-assistive technology.
The research findings have been published in the journal Advanced Functional Materials.
The team is now preparing for clinical trials to validate the device’s effectiveness in medical settings.
