Minimally-intrusive Eyewear Powered by Acoustic Sensing
Cornell University has recently created Echo Speech, a unique eyewear device that is powered by Artificial Intelligence and utilizes Acoustic sensing technology. It is contact free and first SSI (silent-speech interface) on glass-frame. This cutting-edge device is designed to recognize silent speech and eliminates the need for speaking loudly. Echo Speech can recognize lips and turn them into voice, making it a game-changing tool for those with speech disabilities.
Moreover, according to researchers, it would be more socially acceptable than voice speech in places where socially inappropriate to speak loud. Ruidong Zhang, a doctoral student at Cornell University said,
“For people who cannot vocalize sound, this silent speech technology could be an excellent input for a voice synthesizer. It could give patients their voices back,”
With this revolutionary technology, individuals with speech impairments can easily communicate with others in a natural and effortless way. This remarkable invention is set to transform the way we communicate and offers new possibilities for people who previously faced challenges in expressing themselves.
By utilizing speakers and microphones that are fixed onto a glass-frame and emitting inaudible sound waves towards the skin, EchoSpeech is capable of capturing subtle skin deformations that are brought on by silent utterances. EchoSpeech analyzes echoes from multiple paths in order to infer silent speech from the data that it has collected.
“We’re moving sonar onto the body,” said Dr. Cheng Zhang, also from Cornell University.
“It’s small, low-power and privacy-sensitive, which are all important features for deploying new, wearable technologies in the real world.”
“Most technology in silent-speech recognition is limited to a select set of predetermined commands and requires the user to face or wear a camera, which is neither practical nor feasible.”
“There also are major privacy concerns involving wearable cameras — for both the user and those with whom the user interacts.”
The researchers will present their technology(PDF) this month at the Association for Computing Machinery Conference on Human Factors in Computing Systems (CHI’ 23) in Hamburg, Germany.
You may Like Reading:
0 Comments