IIT Guwahati’s new tech to generate artificial voice from vocal cord vibrations

GUWAHATI — Researchers at the Indian Institute of Technology (IIT) Guwahati have developed a novel, low-cost technology that works to generate human speech signals directly from vocal cord vibration signals.

The speech reconstruction technology named ‘LOQU’, derived from the Latin word for ‘to speak or talk’, captures vocal fold movement without invasive procedures, utilising sensors placed over the throat.

This innovative approach allows for the reconstruction of speech signals from vocal cord vibrations, offering promising applications for people with speech impairment like mutism from apraxia, and also in medical settings.

“This breakthrough holds immense promise for individuals facing speech impairments, offering a viable solution with clear and comparable speech signals, as demonstrated in comparison tests. With ‘LOQU,’ we aim to empower those in need and drive impactful innovations in the medical and communication domains,” said Prof. Samarendra Dandapat, Department of Electronics and Electrical Engineering, and lead of the Electro Medical and Speech Technology Group, IIT Guwahati.

“Our method involves capturing vocal fold vibrations using non-invasive sensors and processing these signals electronically to generate speech harmonics. The resulting speech signals closely resemble traditional speech, as validated through comparison tests with signals recorded using conventional microphones,” added Dr. L.N. Sharma of IIT Guwahati.

Importantly, the team conducted extensive comparison tests and determined that the reconstructed speech signals were clear and comparable to traditional speech.

These results hold significant potential for individuals struggling with speech impairments, offering a viable alternative to traditional microphones, and enhancing speech clarity. The patented prototype of LOQU has been developed on a laboratory scale at a cost of under INR 2000, the institute said.