Topic analysis

Hearing aids may cut noise by reading brain signals

A team led by Vishal Choudhari and Nima Mesgarani developed a real-time closed-loop auditory attention decoding (AAD) system that uses intracranial brain signals and machine learning to selectively amplify the conversation a listener focuses on, addressing the 'cocktail party problem' traditional hearing aids struggle with. While the system showed strong accuracy in clinical tests with epilepsy patients (who had existing intracranial electrodes), it requires further research to create a non-invasive version for everyday use, with potential applications in wearable devices like smart earbuds or glasses.