Revolutionary device for vocal function recovery: UCLA’s Innovation

People with voice disorders, such as those stemming from pathological conditions of the vocal cords or recovery from laryngeal cancer surgeries, often face challenges in speaking. However, a potential solution may be on the horizon.

A team of engineers from UCLA has developed a revolutionary device that could aid individuals with dysfunctional vocal cords in regaining their ability to speak. This device is a soft, thin, stretchable patch, slightly larger than 1 square inch, designed to be affixed to the skin outside the throat. The breakthrough technology is outlined in a recent publication in the journal Nature Communications.

Led by Jun Chen, an assistant professor of bioengineering at the UCLA Samueli School of Engineering, the team’s innovation involves a bioelectric system capable of detecting movement in the larynx muscles and translating these signals into audible speech with remarkable accuracy, approaching 95%, thanks to machine-learning technology.

This development marks the latest effort by Chen’s team to assist individuals with disabilities. Previously, they devised a wearable glove capable of translating American Sign Language into spoken English in real-time, facilitating communication for ASL users with non-signers. The new patch-like device comprises two key components: a sensing unit and an actuation unit. The sensing component detects and converts muscle movement signals into electrical signals, which are then translated into speech signals using machine learning. The actuation component converts these signals into the desired voice expression.

Each component consists of biocompatible silicone compound layers with elastic properties and magnetic induction layers made of copper coils. A layer containing PDMS mixed with micromagnets generates a magnetic field. Utilizing a soft magnetoelastic sensing mechanism developed by Chen’s team, the device can detect changes in the magnetic field resulting from laryngeal muscle movements. Serpentine induction coils in the magnetoelastic layers help generate high-fidelity electrical signals for sensing.

Measuring just 1.2 inches on each side and weighing around 7 grams, the device is incredibly thin at 0.06 inches. It can be easily attached to the throat using double-sided biocompatible tape and reused by reapplying the tape as needed.

Voice disorders affect people of all ages and demographics, with nearly 30% of individuals experiencing such disorders in their lifetime. While treatments like surgery and voice therapy exist, recovery can be prolonged, lasting from three months to a year, with some methods requiring significant postoperative voice rest.

Jun Chen, who leads the Wearable Bioelectronics Research Group at UCLA, emphasizes the importance of their device as a non-invasive, wearable option for assisting patients in communicating both before and after treatment for voice disorders, contrasting with existing solutions which can be inconvenient or uncomfortable.

The researchers conducted experiments with eight healthy adults to test the device’s accuracy. They collected data on laryngeal muscle movement and employed a machine-learning algorithm to match these signals to specific words, producing corresponding voice output signals through the device’s actuation component. The system demonstrated an impressive prediction accuracy of 94.68%, effectively amplifying the participants’ voice signals based on their intended sentences.

Moving forward, the research team aims to expand the device’s vocabulary through machine learning and conduct further tests on individuals with speech disorders.

In addition to Jun Chen, the research team includes UCLA Samueli graduate students Ziyuan Che, Chrystal Duan, Xiao Wan, Jing Xu, and Tianqi Zheng, all members of Chen’s lab.

Funding for the research was provided by various organizations including the National Institutes of Health, the U.S. Office of Naval Research, the American Heart Association, the Brain & Behavior Research Foundation, the UCLA Clinical and Translational Science Institute, and the UCLA Samueli School of Engineering.