Khaberni - In a notable scientific advancement, researchers from Pohang University of Science and Technology have successfully developed a new technology capable of converting unspoken speech into audible sound, by analyzing minute movements in neck muscles.
The study, led by Sung Min Park and Sunguk Hong, and published in the journal Cyborg and Bionic Systems, represents an important step towards the development of more advanced communication methods between humans and machines.
How does the technology work?
The idea is based on a simple principle: speech is not only linked to sound but also to precise muscle movements that occur even when attempting to speak silently.
These movements form something like an “invisible map” of words, according to a report published by "digitaltrends".
To capture these signals, the researchers developed a wearable device based on an advanced sensor to detect skin stretch in the neck.
The system consists of a small camera and flexible materials containing reference points, allowing the detection of the finest changes in the skin during silent speech.
Thereafter, the data is analyzed using artificial intelligence techniques where the muscle patterns are interpreted and converted into words and sentences. It can also be combined with sound generation technologies to produce speech that resembles the user's actual voice, even without making any actual sound.
Practical alternative to traditional technologies
Unlike technologies such as electromyography or brain mapping, which require complex and uncomfortable devices, this innovation is lightweight and suitable for everyday use.
During tests, the system demonstrated high accuracy in reconstructing speech, even in noisy environments where traditional microphones fail to operate efficiently.
Wide applications
This technology holds great potential, especially in the medical field, where it can help patients who have lost their ability to speak—due to vocal cord damage or surgical procedures—to regain their ability to communicate using their "own voice".
It can also be used in situations that require silent communication, such as meetings or libraries or busy workplaces, as well as its potential role in developing more natural interfaces between humans and artificial intelligence.
Towards a voiceless future
The researchers are currently working to improve the accuracy of the system and extend its support for multiple languages, with the possibility of integrating it into consumer devices in the future.
This innovation reflects a growing trend towards more seamless interactive technologies, where it may become possible to “hear” words even when they are not actually spoken.
