A small, wearable device powered by artificial intelligence may be able to help people with vocal cord conditions or voice disorders speak.
The soft, thin, flexible bio-electric patch developed by a team of University of California Los Angeles engineers measures just 1.2 square inches and can be worn on the skin outside the throat. It detects the movement in the wearer’s larynx muscles and translates them into audible speech with the help of machine learning technology, and boasts a nearly 95% accuracy.
The breakthrough, led by Jun Chen, an assistant professor of bioengineering at the UCLA Samueli School of Engineering, and his colleagues, was described this week in the journal Nature Communications.
“Existing solutions such as handheld electro-larynx devices and tracheoesophageal- puncture procedures can be inconvenient, invasive or uncomfortable,” said Chen who leads the Wearable Bioelectronics Research Group at UCLA. “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 tiny patch consists of a self-powered sensing component, which detects and converts signals generated by muscle movements into high-fidelity, analyzable electrical signals, which are are then translated into speech signals using a machine-learning algorithm, and an actuation component, which turns those signals into voice expression.
The patch contains micromagnets that generate a magnetic field. A soft magnetoelastic sensing mechanism developed by Chen’s team in 2021 allows it to detect changes in the magnetic field when the laryngeal muscles move.
The device is just 0.06 inches thick and weighs 7 grams, and it has double-sided biocompatible tape that allows it to adhere to the neck, and the tape can be reapplied as needed.
The patch was tested on eight healthy adults who pronounced sentences both aloud and voicelessly, and its accuracy was 94.68%. The researchers hope to expand the device’s vocabulary through machine learning and conduct further testing with people who have speech disorders.
Chen, who has been named one the world’s most highly cited researchers five years in a row, and his team previously developed a wearable glove capable of translating American Sign Language into English speech in real time, allowing ASL users to communicate with those who don’t know how to sign.
According to the researchers, voice disorders are more common than people may think, with nearly 30% of people experiencing such a disorder in their lifetime. In many cases, with surgical interventions and voice therapy, voice recovery can take years. The researchers hope their device will help people continue to communicate while resting their voices after surgery and during the long recovery process.
Story via TMX