A new AI-powered wearable device could help voiceless people speak again

The presentation of this revolutionary technology by UCLA engineers represents an important milestone in the field of advanced communication devices, particularly for people who face communication problems due to conditions such as throat surgery or vocal cord dysfunction.  This innovative device, described in detail in the prestigious journal Nature Communications, offers promising solutions that could potentially change the way we communicate and improve the quality of life of

 human beings suffering from those pathologies.

At the heart of this revolutionary technology is a wearable device measuring approximately one square inch that can be placed on the skin on the outside of the throat. Unlike traditional communication aids, which often rely on external speech synthesizers or invasive procedures, this device uses bioelectric signals from the larynx muscles to produce speech with exceptional precision and an impressive speed of 95%. 

A multidisciplinary team of engineers and researchers led by Jun Chen of the University of California, Los Angeles, has developed a device that consists of two key elements: a self-powered sensor element and an actuator.  Both elements are made of silicone and magnetically induced layers and use innovative materials and technologies to achieve their functionality.

The

sensor element uses magnetoelastic technology, a cutting-edge approach that detects movements of the larynx muscles. These movements are converted into electrical signals, which are then processed by a sophisticated machine learning algorithm. This algorithm plays a key role in interpreting and translating electrical signals into understandable speech signals, ensuring accurate and natural sound.

Meanwhile, the actuator element of the device is responsible for supplying the necessary energy to the motor. This current from the processed electrical signals causes the motor to generate an audio signal, effectively converting the electrical signals into articulated speech. Seamless integration of sensing and actuation components enables real-time communication, allowing users to express themselves clearly and confidently.

What sets this technology apart is not only its exceptional precision, but also its non-invasive nature and user-friendly design. This wearable device eliminates the need for invasive procedures or external speech synthesizers and offers a more comfortable and discreet solution for people with communication difficulties.  Its small size and skin-friendly materials ensure comfort and ease of use, allowing users to seamlessly integrate it into their everyday life.