POSTECH announced on April 2 that Professor Park Sung-min’s research team has developed a groundbreaking technology called silent speech restoration, which uses artificial intelligence to recreate actual voice.
The research was initiated to find innovative ways for patients who have lost their voices due to vocal cord disorders or surgeries to communicate naturally.
The team’s cutting-edge technology combines artificial intelligence (AI) voice synthesis with a wearable sensor that precisely measures minute movements in the throat, enabling voice reproduction without the need for audible sound production.
Professor Park expressed hope that this advancement would accelerate the day when patients with vocal disabilities can reclaim their voices. He also noted that the technology’s applications could extend beyond helping those with vocal impairments, potentially revolutionizing communication in noisy industrial environments such as factories and construction sites.