New AI-driven hearing aid personalises sound for wearers

A new hearing aid has launched that uses artificial intelligence to optimise sound in real time. 

Widex SoundSense Learn processes inputs from connected hearing aids throughout the world and shares the data with a cloud-based AI system. The system can then continuously learn how to optimise hearing aid settings in different situations for specific wearers. The aim is to provide better, more natural and personalised sound for hearing aid users

The hearing aid gives users A-B comparisons to choose from, so it can begin understanding how the wearer prefers sound in different environments. It manages low, mid, and high frequencies that which can each be set to 13 different levels, resulting in more than 2,000 possible settings. 

Widex say that to test each setting would require doing more than 2 million tests, but by using machine learning algorithms it only needs a dozen comparisons to calculate the optimal settings for each person. The algorithms also track the user’s individual adjustments, such as how often they change the volume and which sound presets they most regularly use.

The wearer can store the settings as programs on their smartphone, and activate them throughout the day, such as when they’re at work, at the supermarket, or in their kitchen. These programs can also be stored, anonymised, in the cloud, to help enhance the hearing experience of other users.

“Our studies show that hearing aid users have a significant preference for the personalised settings achieved through artificial intelligence and machine learning, and that 80 percent would recommend the function to others” Widex Head of Audiology Lise Henningsen said. 

“By applying artificial intelligence, a hearing solution learns how users prefer various listening environments and gives them greater control over their hearing experience" she added.