Cornell University Students Develop SpeeChin, a Smart Necklace That Recognizes Silent English and Mandarin Speech Commands

In case of emergency, when you’re unable to make a sound, the SpeeChin silent speech recognition device will be able to help. This innovative smart necklace was developed by Cornell University students and basically utilizes a neck-mounted infrared camera to recognize movements in the chin and throat. These movements, which can be silently mouthed voice commands, are then translated to either computer or smartphone actions.

SpeeChin consists of an infrared camera mounted on a 3D-printed necklace case, which is hung on a silver chain with the camera pointing up at the wearer’s chin. To keep things more stable, the students designed a wing on each side, and then placed a coin on the bottom for extra weight. During the testing phase, participants mouthed 54 commands in English, consisting of digits, interactive commands, voice assistant commands, punctuation commands and navigation commands as well as 44 simple Mandarin words or phrases. The device recognized commands in both English and Mandarin with an average accuracy of 90.5% and 91.6%, respectively.

10,201 Reviews

Apple Watch Series 7 [GPS 45mm] Smart Watch w/Midnight Aluminum Case with Midnight Sport Band. Fitness...

WHY APPLE WATCH SERIES 7 — The most advanced Apple Watch features powerful health innovations like sensors and apps to measure your blood oxygen and...
EASILY CUSTOMIZABLE — Available in a range of sizes and materials, with dozens of bands to choose from. Change up your look by switching your band...
INCREDIBLE DURABILITY — Built to be tough. It’s more crack resistant, it’s dust resistant, and it’s swimproof.

There are two questions: First, why a necklace? And second, why silent speech? We feel a necklace is a form factor that people are used to, as opposed to ear-mounted devices, which may not be as comfortable. As far as silent speech, people may think, ‘I already have a speech recognition device on my phone.’ But you need to vocalize sound for those, and that may not always be socially appropriate, or the person may not be able to vocalize speech,” said Ruidong Zhang, doctoral student.