Trending: Taste-testing the Cosmic Crisp, Washington state’s star-studded ‘apple of the future’
Orbityl’s earbuds can detect mental states as well as a few distinct thoughts — after a lot of calibration. Co-founder Kristina Pearkes demos the startup’s prototype. (Orbityl Photo)

What if you could control the volume of your headphones with a thought?

Vancouver, B.C.-based startup Orbityl wants to make that happen with a brain-computer interface that looks like an ordinary pair of headphones.

The startup is currently partnering with a headphone manufacturer to make a product that can sense a user’s mental state — i.e. whether they’re awake, asleep, and how alert they are. That’s the first application, which works by sensing the change in voltage in the brain over time. They haven’t yet disclosed the identity of the hardware maker.

The more ambitious plan is to use machine learning to decode thoughts.

Orbity co-founders Sean Kaiser and Kristina Pearkes. (Orbityl Photo)

“A lot of the research that we’ve done is in brain-computer interface applications — looking for discrete thoughts that an individual is having as a mechanism to be used for control [of a device],” said Orbityl co-founder Sean Kaiser.

The startup, which first launched two years ago, is working out of the VentureLabs accelerator at Simon Fraser University in Vancouver. Orbityl raised around $120,000 from the Next 36 program in Toronto and the Highway1 accelerator in San Francisco, and it’s looking to add team members in the coming months.

Orbityl plans to start small, training its algorithms to recognize basic commands. For instance, if you’re listening to music, you might think “right” to skip a track or “up” to raise the volume.

Both Kaiser and co-founder Kristina Pearkes studied at McGill University in Montreal. Pearkes brings the electronics hardware knowledge and Kaiser is the machine learning expert.

Right now, their prototype can recognize basic thoughts from Kaiser’s brain, but it struggles with other users.

“One of the challenges in developing this stuff is that you need a lot of examples to train the algorithms,” Kaiser said. “The calibration time is very high for other individuals to use, so that’s where a lot of our research is going right now.”

Brain-computer interfaces are a longtime sci-fi moonshot, but there are signs that the tech might be moving out of the experimental phase.

Earlier this month, Mark Zuckerberg revealed that Facebook is researching the technology. The FDA last month released draft guidance on brain-computer interfaces for medical applications. And Elon Musk’s secretive Neuralink venture, the subject of an exhaustive deep dive from the Wait But Why blog, is exploring the space.

Mind-machine ambitions aside, Kaiser says there’s also plenty of value simply making mental state detection easier. Doctors and researchers often use an electroencephalogram (EEG), essentially a bunch of electrodes attached to your head, to monitor brain activity. Kaiser thinks that a more practical device could make it easier to do some kinds of research and testing.

“We started by looking at sleep. So we were looking at these EEGs and we saw this issue in sleep monitors. You have to go to a clinic, and you have to get these things set up. And it was a big barrier to a lot of individuals that created a lot of waiting time,” Kaiser said.

Like what you're reading? Subscribe to GeekWire's free newsletters to catch every headline

Comments

Job Listings on GeekWork

Find more jobs on GeekWork. Employers, post a job here.