Skip to content

Scientists Create Mind-Controlled Hearing Aid

May 16, 2019

A mind-controlled hearing aid that allows the wearer to focus on particular voices has been created by scientists, who say it could transform the ability of those with hearing impairments to cope with noisy environments.

The device mimics the brain’s natural ability to single out and amplify one voice against background conversation. Until now, even the most advanced hearing aids work by boosting all voices at once, which can be experienced as a cacophony of sound for the wearer, especially in crowded environments.

Nima Mesgarani, who led the latest advance at Columbia University in New York, said: “The brain area that processes sound is extraordinarily sensitive and powerful. It can amplify one voice over others, seemingly effortlessly, while today’s hearing aids still pale in comparison.”

This can severely hinder a wearer’s ability to join in conversations, making busy social occasions particularly challenging.

Scientists have been working for years to resolve this problem, known as the cocktail party effect. The brain-controlled hearing aid appears to have cracked the problem using a combination of artificial intelligence and sensors designed to monitor the listener’s brain activity.

The hearing aid first uses an algorithm to automatically separate the voices of multiple speakers. It then compares these audio tracks to the brain activity of the listener. Previous work by Mesgarani’s lab found that it is possible to identify which person someone is paying attention to, as their brain activity tracks the sound waves of that voice most closely.

The device compares the audio of each speaker to the brain waves of the person wearing the hearing aid. The speaker whose voice pattern most closely matches the listener’s brain waves is amplified over the others, allowing them to effortlessly tune in to that person.

The scientists developed an earlier version of the system in 2017 that, while promising, had the major limitation that it had to be pre-trained to recognise speakers’ voices. Crucially, the latest device works for voices it has never heard before.

To test the device, the lab recruited epilepsy patients who already had electrodes implanted in their brain to monitor seizure activity ahead of planned brain surgery.

The patients were played audio of different speakers simultaneously while their brain waves were monitored via the electrodes implanted into their brain.

An algorithm tracked the patients’ attention as they listened to different speakers that they had not previously heard. When a patient focused on one speaker, the system automatically amplified that voice, with a lag of just a few seconds. When their attention shifted to a different speaker, the volume levels changed to reflect that shift.

The current version of the hearing aid, which involved direct implants into the brain, would be unsuitable for mainstream use. But the team believe it will be possible to create a non-invasive version of the device within the next five years, which would monitor brain activity using electrodes placed inside the ear, or under the skin of the scalp.

In theory, Mesgarani said, the device could also be used like a pair of audio “binoculars” to covertly listen in on people’s conversations, although this was not the intended application.

The next step will be testing the technology in those with hearing impairments. One question is whether it will be as easy to match up brain activity in people who are partially deaf with sound waves from speech. According to Jesal Vishnuram, technology manager at the charity Action on Hearing Loss, said that one of the reasons people find conventional hearing aids unpleasant in noisy environments is that their brain is out of practice at filtering sounds and so does this less effectively.

“One of the reasons people struggle is that they often wait a long time before getting a hearing aid and in that time the brain forgets how to filter out the noise and focus on the speech,” she said. “This is really interesting research and I’d love to see the real world impacts of it.”

The findings are published in the journal Science Advances.

No comments yet

What are you thinking?

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: