A team of engineers from the University of California has developed an elastic device measuring about 3 cm that can be attached to the skin on the neck to help people with dysfunctional vocal cords restore their voice function, reports TechXplore.

A new bioelectrical system developed by Jun Chen, an assistant professor of bioengineering at the Samueli School of Engineering at the University of California, Los Angeles, is able to detect the movement of human laryngeal muscles and convert these signals into spoken language using machine learning technology – with an accuracy of almost 95%.

Earlier, Jun Chen and his team developed a glove that can translate American Sign Language into English in real time to help the mute communicate with those who do not know sign language.

The new tiny device, which looks like a band-aid, consists of two components. The first, a self-powered sensor component, detects and converts muscle movements into highly accurate electrical signals that can be analyzed. These electrical signals are then converted into speech signals using a machine learning algorithm.

The second component, the actuator, converts these speech signals into the desired voice expression.

Each of these two components contains two layers: a layer of biocompatible polydimethylsiloxane (PDMS) silicone compound with elastic properties and a magnetic induction layer made of copper induction coils. Between these two components is a fifth layer containing PDMS mixed with micromagnets, which generates the magnetic field.

Using a soft magnetoelastic sensor mechanism, the device is able to detect changes in the magnetic field due to mechanical forces – in this case, laryngeal muscle movement. Built-in induction coils in the magnetoelastic layers help generate highly accurate electrical signals for sensing purposes.

The device weighs about 7 grams and is about 50 mm thick. Thanks to the double-sided biocompatible tape, it can be easily attached to the human throat near the vocal cords and can be reused.