AI-Powered Wearable Helps Users Regain Voice

University of California (UCLA) researchers have created an AI-powered wearable to help people with voice disorders speak again.

The adhesive neck patch, measuring just over one inch, is placed on a user’s throat and detects movement in a wearer’s larynx muscles, which are translated into audible speech using machine learning technology.

“Existing solutions such as handheld electro-larynx devices and tracheoesophageal puncture procedures can be inconvenient, invasive or uncomfortable,” said Jun Chen, study lead. “This new device presents a wearable, non-invasive option capable of assisting patients in communicating during the period before treatment and during the post-treatment recovery period for voice disorders.”

The team demonstrated the system’s efficacy in tests, having participants say five sentences both aloud and voicelessly, with a near 95% accuracy.

The UCLA team previously developed a wearable glove that translates American Sign Language into English speech in real time, helping ASL users communicate with those who can’t sign. 

The team said it plans to expand the vocabulary of the device through machine learning and to test it in people with speech disorders.