New Delhi: Researchers at the Indian Institute of Technology (IIT) Guwahati and Ohio State University, USA, have developed an underwater vibration sensor that enables automated and contactless voice recognition.

They said the sensor offers a promising alternative communication method for individuals with voice disabilities who are unable to use conventional voice-based systems. The findings have been published in the journal Advanced Functional Materials.

According to Uttam Manna, Professor in the Department of Chemistry at IIT-Guwahati, voice recognition has become an integral part of modern life, helping users operate smart devices through voice commands. However, for people with voice disorders, this technology remains inaccessible.

“Recent studies show that a noticeable percentage of children and young adults between 3 and 21 experience some form of voice disability, underscoring the need for more inclusive communication technologies,” Manna said.

To address this limitation, the team focused on the air exhaled through the mouth while speaking. Even when individuals cannot produce sound, attempting to speak generates airflow from their lungs. When this air flows over a water surface, it creates subtle waves.

The researchers developed an underwater vibration sensor that detects these water waves and interprets them as speech signals without relying on audible voice, creating a new avenue for voice recognition. The sensor is made from a conductive, chemically reactive porous sponge. When placed just below the air-water interface, it captures tiny disturbances created by exhaled air and converts them into measurable electrical signals.

They used Convolutional Neural Networks (CNN), a type of deep learning model, to accurately recognise these subtle signal patterns, allowing users to communicate with devices from a distance without needing to generate sound.

“It is one of the rare material designs that recognises voice by monitoring water waves formed at the air-water interface due to exhaled air. This may offer a viable solution for those with partially or entirely damaged vocal cords,” Manna said.

The working prototype costs around Rs 3,000 at lab scale. With potential industry collaboration, the price is expected to drop.

The team now plans to obtain clinical validation and collect more datasets from individuals with voice disabilities to refine the model for recognising specific words or phrases when exhaled air is directed over a water surface. Beyond voice recognition, the sensor could be used for hands-free device operation, exercise tracking, movement detection, and underwater sensing and communication, Manna added.