A person can lose their voice from a cold, constantly speaking as a teacher, singing at the top of their voice at a concert, or from allergies – but they always recover.
However, there are diseases that cause vocal cord paralysis, in which you cannot control the movement of the muscles that control your voice when the nerve impulses in your voice box (larynx) are affected. . This results in permanent paralysis of the vocal cord muscles.
Vocal cord paralysis can also make it difficult to speak and breathe. This is because your vocal cords not only produce sound but also protect your windpipe by preventing food, drink and even your saliva from entering your windpipe and choking you. Is. Possible causes of vocal cord paralysis include certain cancers, nerve damage during surgery, cervical spine injuries, and even serious viral infections.
However, there is hope for people who have chronically or permanently lost their voice – a new wearable, adhesive device that uses artificial intelligence by bioengineers at the University of California, Los Angeles (UCLA) has prepared Just over 6.5 square centimeters can be attached to the skin on the outside of the throat to help people with dysfunctional vocal cords regain voice function.
The invention has been disclosed in the prestigious journal Nature Communications, titled “Speech without vocal folds using a wearable sensing activation system powered by machine learning”.
The bioelectric system, developed by Prof. Jun Chen and his colleagues at UCLA’s Samueli School of Engineering, uses machine learning technology to detect movement in a person’s larynx muscles and transmit those signals with about 95 percent accuracy. Able to translate into audible speech. .
This is the latest development in Chan’s efforts to help people with disabilities. His team developed the first wearable gloves capable of translating American Sign Language (ASL) into English speech in real time to help ASL users communicate with people who sign. do not know
Patch design
The tiny new patch-like device consists of two components. A self-powered sensing component detects signals generated by muscle movements and converts them into high-fidelity, analyzable electrical signals. These electrical signals are then translated into speech signals using machine learning algorithms. The second, an activation component, converts these speech signals into the desired vocal expression.
Each of the two components consists of two layers: a layer of the biocompatible silicone compound polydimethylsiloxane (PDMS) with flexible properties and a magnetic induction layer made of a copper induction coil. Sandwiched between the two components is a fifth layer consisting of PDMS mixed with micromagnets, which generate a magnetic field.
Using a soft magnetoelastic sensing mechanism developed by Chen’s team three years ago, the device can detect changes in the magnetic field when it is altered by mechanical forces—in this case, the laryngeal muscles. movement Serpentine induction coils embedded in magnetic layers help generate high-fidelity electrical signals for sensing purposes.
Measures 3 cm. On each side, the device weighs around 7 grams. And is only 1.5 mm. With thick double-sided biocompatible tape, it can easily stick to a person’s throat near the location of the vocal cords and can be reused by reapplying the tape as needed.
Voice disorders occur in all age and demographic groups. Research shows that about one-third of people will experience at least one such disorder in their lifetime. Yet with treatment methods, such as surgical intervention and voice therapy, voice recovery can extend from three months to a year, with some invasive techniques requiring a significant period of mandatory voice rest after surgery.
“Current solutions such as handheld electro-larynx devices and tracheoesophageal-puncture procedures can be painful, invasive or uncomfortable,” said Chen, who has been named the world’s most cited researcher for five consecutive years. has been given. “This new device offers a wearable, non-invasive option to help patients communicate during the pre-treatment period and during the rehabilitation period after treatment for voice disorders.”
In their experiments, the researchers tested the wearable technology on eight healthy adults. They collected data on laryngeal muscle movements and used machine learning algorithms to associate the resulting signals with certain words and then select the corresponding output voice signal through the device’s activation component.
The research team asked participants five sentences – both aloud and silent – including “Hi, Rachel, how are you today?” By showing how accurate the system is. And I love you!” The overall prediction accuracy of the model was 94.68%, with the participants’ vocal signal amplified by the activation component, indicating that the sensing mechanism had captured their laryngeal movement signal. Recognized and matched the same sentence that the participants wanted to say.
Looking ahead, the research team plans to expand the device’s vocabulary through machine learning and test it in people with speech impairments.