Hearing aid: Brainwaves recognize and filter voices

Hearing aids struggle in noisy environments. US scientists use brainwaves to filter out individual voices from the background.

listen Print view
Hearing aid in the ear of an elderly person

(Image: Zay Nyi Nyi / Shutterstock.com)

2 min. read

The human ear does much more than just perceive sounds. In a noisy environment, for example, it can filter out noises so that voices are perceived better. Technical devices like conventional hearing aids cannot do this, which is why hearing-impaired people have difficulty following conversations in noisy environments.

A research team led by Nima Mesgarani at Columbia University New York has developed a hearing aid that can filter out individual voices from a cacophony using brainwaves. An electrode detects when the person is concentrating on one of two conversations and amplifies it. The other is suppressed, the team writes in the journal Nature Neuroscience.

Mesgarani and his team tested the system on epilepsy patients who already had an electrode implanted in their brain to locate the origin of seizures. The researchers used these to record the subjects' brain activity.

The team then played two overlapping conversations to the subjects and instructed them to concentrate on one of them. The system automatically detected which one the test person was following. It amplified this in real-time while quieting the other.

“We have developed a system that acts as a neural extension of the user, leveraging the brain’s natural ability to filter through all the sounds in a complex environment to dynamically isolate the specific conversation they wish to hear,” said Mesgarani. It worked so well that one test subject even accused the researchers of only playing one conversation to her.

Videos by heise

Mesgarani has been working on this topic for about a decade and a half: in 2012, he succeeded in identifying the brain signals associated with listening to a specific conversation. The team linked the peaks and troughs in brainwaves to speech and pauses in the conversation. Building on this, the team has developed algorithms that can isolate individual voices from a group and compare each voice in the round with brainwaves.

The work shows that it is possible to develop a system that recognizes brainwaves in real-time and selectively enhances a conversation, said Vishal Choudhari, the lead author of the study.

The New York-based team aims to develop a hearing aid that can replicate the selective perception of human hearing.

(wpl)

Don't miss any news – follow us on Facebook, LinkedIn or Mastodon.

This article was originally published in German. It was translated with technical assistance and editorially reviewed before publication.