- AI is used to turn neck movements into words
- This is the work of South Korean researchers
- The system could potentially be used for “silent conversations”
One of the many talents offered by AI systems is advanced pattern recognition, and researchers at Pohang University of Science and Technology (POSTECH) in South Korea have put this to good use by developing a wearable neckband that translates muscle and skin movements into speech.
As the researchers pointed out (via New Atlas), the device is intended to restore “lost voices” — to give the power of speech back to those who are unable to speak normally. A small camera is used to track a “motion map” on the neck when the wearer intends to say something, without any vocalization being necessary.
The algorithm-based estimation of what a person is trying to say is then combined with text-to-speech technology to verbalize the words. This text-to-speech system can even be trained on the wearer of the AI lanyard (an example of deepfake technology actually being used for something worthwhile).
Article continues below
“This is a remarkable technology because it has a wide range of potential applications, including assisting laryngectomy patients, communicating in noisy industrial environments, and even supporting silent conversations,” says Professor Sung-Min Park, who led the study at POSTECH).
Recognition accuracy of 85.8%
These “silent conversations” can take place in libraries or conference rooms, for example, when people are not able to speak audibly for whatever reason. It could even be used as an alternative to radios or text messaging for staff working in an area where it is impractical to hold face-to-face conversations.
However, there is still a long way to go before everyone can use it. Although the group can achieve recognition accuracy of 85.8%, this is only for 26 predefined words – the NATO phonetic alphabet (“Alpha”, “Bravo”, etc.). On the other hand, when the subject is moving, the accuracy rate currently drops to 39.72%.
This rate is expected to improve as the system is further trained. Encouragingly, the neckband worked well when it came to suppressing background noise, and words could be recognized with white noise levels of 90 decibels in the background (roughly the equivalent of a busy construction site).
Another advantage of the wearable AI system is that it is much simpler and less bulky than other thought-speech systems currently in development, including technology based on reading brain waves through electroencephalography (EEG). This is a significant step forward in terms of portability and accessibility.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds. Make sure to click the Follow button!
And of course you can also follow TechRadar on YouTube And TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
The best laptops for every budget
