(ORDO NEWS) — For those who have lost their voice due to surgery or some other medical condition, life can be very difficult.
Now a team of researchers at Beijing Tsinghua University has developed a simple device that can bring speech back to the mute.
The new instrument is a one-centimeter square that can be easily attached to the throat to convert barely audible sounds and whispers into speech audible at normal volume.
The researchers call the invention an “intelligent, wearable graphene-based artificial throat” and is powered by a coin-sized battery.
Research team leader Professor Ren Tianling explained that the innovation is able to recognize and translate speech elements such as phonemes, tones and words with up to 99 percent accuracy, according to TechXplore.
This is achieved by using an artificial intelligence model to interpret captured sounds and body vibrations to generate vocalizations.
“Its workable voice manufacturing process, stable performance, noise tolerance, and integrated vocalization make the device a promising tool for next-generation speech recognition and interaction systems,” said Tianling.
He also explained that the new chip’s graphene sensors are ideal for detecting tiny vibrations on skin surfaces.
The device, he says, “can sense muscle movements and sound vibrations transmitted to the surface of the skin” and “translate recognizable mechanical information into speech.”
Noise interference is not a problem
What’s more, interference from noisy, harsh environments such as highways, fires, and aircraft cabins does not affect the device.
It continues to function at an optimal level regardless of the environment in which it is placed.
“The speaker’s health conditions, such as neurological disease, cancer, injury, as well as the environment, noise interference, and transmission environment often affect sound transmission and recognition,” Tianling said.
These circumstances do not affect the chip, which is able to function despite any external interference.
More research is needed to make vocalizations more expressive, but the researcher believes the device is practical and effective enough to become commonplace in the future.
“Our smart machine provides a new speech recognition paradigm and is expected to pave the way for mechanical sensor applications in smart home health monitoring systems, wearable electronics and even cryptographic security,” he said.
—
Online:
Contact us: [email protected]
Our Standards, Terms of Use: Standard Terms And Conditions.