The IIT Guwahati Research Team.
Credit: IIT Guwahati
Guwahati: The Indian Institute of Technology Guwahati (IIT-Guwahati) on Tuesday claimed that its researchers achieved a significant breakthrough in speech technology by developing a novel method to generate human speech signals directly from vocal cord vibration signals.
A statement issued by IIT-G said the "breakthrough" holds immense promise for individuals facing speech impairments, offering a viable solution with clear and comparable speech signals, as demonstrated in comparison tests.
It said a research team headed by Samarendra Dandapat, a professor of department of Electronics and Electrical Engineering and L.N. Sharma of IIT Guwahati, created a technology named "LOQU" (derived from the Latin word for To speak or talk) which can capture vocal fold movement without invasive procedures, utilizing sensors placed over the throat. "This innovative approach allows for the reconstruction of speech signals from vocal cord vibrations, offering promising applications for speech-impaired individuals and medical settings," said the statement.
The team also includes Pharvesh Salman Choudhary, Sibasis Sahu, Debasis Jyotishi, Moirangthem James Singh, Samarjeet Das, and Yengkhom Omesh Singh.
"With 'LOQU,' we aim to empower those in need and drive impactful innovations in the medical and communication domains,” said the statement quoting Dandapat.
The statement said speech production begins with airflow from the lungs through the windpipe, facilitated by the larynx or voice box, which acts as a conduit between the throat and windpipe. Inside the larynx are the vocal cords or vocal folds, regulated by the glottis, controlling airflow between the lungs and mouth. The voice box adjusts the space between vocal folds to create sounds, which travel through the vocal tract, modulating in volume and pitch to form "voice."
During speech, vocal folds vibrate due to intrinsic laryngeal muscle movement. In some cases, like mutism from apraxia, individuals may have normal vocal fold vibration without sound production due to coordination issues in tongue or throat muscles essential for speech.
Quoting Sharma, the statement said, "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."
The reconstructed speech signals have been found to be clear and comparable to traditional speech in extensive comparison tests. These results hold significant potential for individuals struggling with speech impairments, offering a viable alternative to traditional microphones, and enhancing speech clarity.
The prototype of LOQU, which has also been granted patent, is priced at around Rs 2,000, it said.