“By applying AI, a hearing solution learns how users prefer various listening environments and gives them greater control over their hearing experience,” commented Widex Head of Audiology Lise Henningsen. “By being the first to embrace AI, Widex benefits from years of continuous machine learning and hearing aid optimisation that other hearing aid manufacturers have not yet developed.”
Powered by AI, SoundSense Learn processes inputs from connected hearing aids throughout the world and shares anonymised data with a cloud-based AI system. The system then continuously learns how to further optimise hearing aid settings in different situations for specific wearers.
SoundSense Learn presents users with A-B comparisons to begin understanding how a person wearing compatible Widex hearing aids prefers sound in an environment. The system manages three acoustic parameters - low, mid, and high frequencies - which can each be set to 13 different levels, resulting in more than 2,000 possible settings.
To A-B test each setting would require more than 2 million tests, but by using the power of machine-learning algorithms, SoundSense Learn requires only about a dozen comparisons to calculate the optimal settings for the individual person.
The algorithms are able to track the user’s individual adjustments and draw from other user settings stored in the cloud to more precisely tailor the hearing aids to one’s surroundings. When applied, the settings create a personalised hearing experience based on context, content, and intent.
Users can store the settings as programs in their smartphones and activate them throughout the day, such as when they’re at work, at the supermarket, or in their kitchen. Anonymised, the programs can also be stored in a secure, cloud-based system and 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,” Henningsen added.
