
"Current hearing aids are good at amplifying sounds and voices, but they struggle with the classic 'cocktail party problem' deciding which voice matters to the listener. It can take a lot of effort to focus your attention on one voice in a crowded room. Hearing is not only about whether words are understood correctly. Two people may both understand [what they're saying], but one person may need far more mental effort to follow the conversation. That can become exhausting over time."
"So, Choudhari and his colleagues are trying to develop a smart technology that knows what a hearing aid user is listening to. They want to enhance that one sound or voice, while at the same time reducing the volume of any other sounds, voice or background noise. And to do that, they designed a system that reads brain waves and, using artifical intelligence, interprets what a listener is listening to."
"Many hearing aids use beamforming, which enhances sounds coming from a certain direction, usually in front of the listener. But real conversations are dynamic. People turn their heads, switch attention, or even listen to someone without directly looking at them. Real-time machine learning algorithms could examine brain waves and interpret listening focus."
Current hearing aids amplify sounds and voices but do not reliably solve the cocktail party problem of choosing which voice matters. Following conversations in crowded places can require substantial mental effort, leading some people to stop using hearing aids when they need them most. Researchers aim to build smart hearing technology that identifies what a listener is attending to, then enhances that voice while reducing other voices and background noise. The proposed system reads brain waves and uses artificial intelligence to interpret listening focus. Existing beamforming approaches enhance sounds from a fixed direction, but real conversations involve head turns and shifting attention, so the system must adapt dynamically to changing focus.
#hearing-aids #cocktail-party-problem #brain-computer-interfaces #machine-learning #auditory-attention
Read at www.dw.com
Unable to calculate read time
Collection
[
|
...
]