Optical BCI: Silent Speech – Close, But Not Close enough (Yet)

Housed in its top-secret Skunkworks tucked away in Building 8 on Meta’s campus in Menlo Park, Facebook Reality Labs (FRL) worked on a project to build a headset or headband to allow people to send text messages by thinking – tapping them out at 100 words per minute.

Though last year Facebook decided to put this ‘silent speech’ project on the backburner for a while, Regina Dugan, who was then head of the Building 8 hardware division, remains a believer. “It sounds impossible but it’s closer than you realise,” she told Technology Review.

Giving AR and VR a HandSean Keller, Meta’s head of research, is inventing soft, lightweight haptic gloves that can bring full hand presence into AR and VR. (source ©: Facebook)

It now seems it was not quite close enough. In a blog post last April, FRL research director Sean Keller said the team was happy to say that “for the first time, someone with severe speech loss has been able to type out what they wanted to say almost instantly, simply by attempting to speak”. However, he added that Facebook decided to transfer its results to the broader neuroscience community, effectively releasing it into the wild where it will continue its existence as an open-source project.

Touchie FeelieTo deliver a realistic sense of touch, a haptic glove needs hundreds of actuators (tiny motors) all over the hand, moving in concert in a way that makes the wearer feel like they’re touching a virtual object. (source ©: Facebook)

“While we still believe in the longterm potential of headmounted optical BCI technologies, we’ve decided to focus our immediate efforts on a different neural interface approach that has a nearer-term path to market: wrist-based devices powered by electromyography,” he explained. Electromyography (EMG) is a technique for analysing and recording the electrical activity produced by skeletal muscles.

Scientists from the University of San Francisco working with Facebook have developed a wear-able prototype that uses near-infrared light to mea-sure blood oxygenation in the brain and indirectly measure brain activity in a safe, non-invasive way. (source ©: Facebook)

EMG can pick up and decode the signals for hand and finger movements at the wrist and translate them into digital commands for a device. In the near term, these signals will let people communicate with their devices with a degree of control that’s highly reliable, subtle, personalisable and adaptable to many situations. As this area of re-search evolves, EMG-based neural interfaces have the potential to dramatically expand the bandwidth with which we can communicate with our devices, opening up the possibility of things like high-speed typing.

READ MORE ARTICLES