Researchers Develop a Vocal Patch to Speak Without Vocal Cords
American scientists from the University of California at Los Angeles have created a patch that enables speech without relying on the vocal cords. The team published their findings in Nature Communications, a respected scientific journal. This cutting edge work reveals a compact device that listens for throat movements during speech, then turns those movements into electrical signals that can be decoded into spoken language.
The patch is small and flexible. It detects subtle throat contractions generated while forming speech and uses these cues to generate electricity, eliminating the need for batteries. The technology hinges on galfenol, an iron gallium alloy whose magnetic state shifts when it is compressed or deformed. When the patch experiences slight tension from the throat muscles, galfenol responds by producing electrical signals that a separate system translates into speech.
Construction of the device features five ultra thin layers. The outer shell is a soft, flexible silicone skin that comfortably interfaces with the neck area. The core houses micromagnets which create a magnetic field that varies with throat movement. Surrounding these magnets are two copper wire layers that function as coils, converting changes in magnetism into usable electrical signals for processing.
Those electrical signals are then fed into a machine learning system that interprets the pulses and renders them as spoken words. In demonstrations with eight participants who did not have speech impairments, the algorithm translated the patch signals into speech with high accuracy, achieving about 95 percent in the tested scenarios.
Previous work in this area has explored electronic skin that can be produced with 3D printing techniques, showing a broader push toward wearable interfaces that convert body activity into digital outputs. The UCLA study builds on this trajectory by combining flexible materials, a galfenol core, and an integrated signal processing pipeline to deliver real time speech without conventional vocalization. The researchers note that while the current results are promising, ongoing testing and refinement are planned to expand vocabulary, improve robustness, and address real world use cases. The research team emphasizes careful consideration of safety, comfort, and user experience as the technology moves toward potential clinical and assistive applications. [Citation: UCLA press release, Nature Communications thank you to the study authors for details in this summary]