People with voice disorders, including those with pathological conditions of the vocal cords or recovering from laryngeal cancer surgery, may often have difficulty or difficulty speaking. That may change soon.
A team of UCLA engineers has invented a soft, thin, elastic device measuring just 1 square inch that can be attached to the skin on the outside of the throat to help people with dysfunctional vocal cords regain their vocal function. Their progress is detailed this week in the magazine Nature communications.
The new bioelectric system, developed by Jun Chen, assistant professor of bioengineering at the UCLA Samueli School of Engineering, and his colleagues, is able to detect movement in a person’s larynx muscles and translate those signals into audible speech with machine-assisted learning technology -? with almost 95% accuracy.
The breakthrough is the latest in Chen’s efforts to help people with disabilities. His team previously developed a wearable glove capable of translating American Sign Language into English speech in real time to help ASL users communicate with those who do not know how to sign.
The tiny new patch-like device consists of two components. One, a self-powered sensing element, detects and converts signals generated by muscle movements into high-fidelity, analyzable electrical signals. These electrical signals are then translated into speech signals using a machine learning algorithm. The other, an actuation element, converts these speech signals into the desired vocal expression.
The two components each contain two layers: a layer of biocompatible polydimethylsiloxane silicone compound, or PDMS, with elastic properties, and a magnetic induction layer of copper inductance coils. Between the two components is a fifth layer containing PDMS mixed with micromagnets, which creates a magnetic field.
Using a soft magnetoelastic sensing mechanism developed by Chen’s team in 2021, the device is able to detect changes in the magnetic field when it changes as a result of mechanical forces -. in this case, the movement of the muscles of the larynx. Integrated serpentine inductors in the magnetoelastic layers help generate high-fidelity electrical signals for sensing purposes.
Measuring 1.2 inches on each side, the device weighs around 7 grams and is just 0.06 inches thick. With biocompatible double-sided tape, it can be easily attached to a person’s neck near the vocal cord location and can be reused by reapplying tape as needed.
Voice disorders are common across all ages and demographics. research has shown that nearly 30% of people will develop at least one such disorder in their lifetime. However, with therapeutic approaches such as surgery and voice therapy, voice recovery can take anywhere from three months to a year, with some invasive techniques requiring a significant period of mandatory post-operative vocal rest.
“Existing solutions such as wearable electrolaryngeal devices and tracheoesophageal puncture procedures can be uncomfortable, invasive or uncomfortable,” said Chen, who leads the Wearable Bioelectronics Research Group at UCLA, and has been named one of the world’s most popular researchers five years in a row. “This new device presents a portable, non-invasive option capable of assisting patients with communication during the pre-treatment period and during the recovery period after treatment for voice disorders.”
How machine learning is enabling wearable technology
In their experiments, the researchers tested the wearable technology on eight healthy adults. They collected data on laryngeal muscle movement and used a machine learning algorithm to associate the resulting signals with certain words. They then selected a corresponding output voice signal via the device’s activation element.
The research team proved the system’s accuracy by having participants say five sentences -? both loud and voiceless -? including “Hi Rachel, how are you today?” and I love you!”
The overall prediction accuracy of the model was 94.68%, with the participants’ vocal signal amplified by the actuation element, showing that the sensory mechanism recognized the laryngeal movement signal and matched the corresponding sentence the participants wanted to say.
Going forward, the research team plans to continue expanding the device’s vocabulary through machine learning and testing it on people with speech disorders.
Other authors of the paper are UCLA graduate students Samueli, Ziyuan Che, Chrystal Duan, Xiao Wan, Jing Xu and Tianqi Zheng -? all members of Chen’s lab.
The research was funded by the National Institutes of Health, the US Office of Naval Research, the American Heart Association, the Brain and Behavior Research Foundation, the UCLA Clinical and Translational Science Institute, and the UCLA Samueli School of Engineering.
Source:
Journal Reference:
Che, Z., et al. (2024). Speaking without vocal folds using a mobile machine learning-assisted detection-activation system. Nature communications. doi.org/10.1038/s41467-024-45915-7.
