Common configurations and personalization systems for over-the-counter hearing aids

Sensorineural hearing loss can significantly impact an individual’s lifestyle if left untreated. It can lead to lifestyle-related dementia, social isolation, and depression. Due to the higher costs of hearing health care and traditional methods of fitting hearing aids, a significant population who could benefit from using hearing aids do not use them. Over-the-counter hearing aids enable more affordable and accessible hearing health care by shifting the burden of configuring the device from trained audiologists to end-users. A critical challenge is to provide users with an easy-to-use method for personalizing the many parameters which control sound amplification based on their preferences.

There are five core contributions of my Ph.D. thesis: i) Development of common hearing aids configurations for mild-to-moderate hearing loss: Our approach is based on using US population data with hearing loss and using a clustering approach to find common hearing aid configurations that cover a large US population with hearing loss. ii) Simulation framework to evaluate hearing aids personalization algorithms: We propose a method that can use exhaustive pairwise comparison data of hearing aid users to simulate user behavior and evaluate different personalization algorithms. iii) Personalization of over-the-counter hearing aids: We propose a novel personalization algorithm that leverages the relationship between different hearing aid configurations for faster personalization. iv) Development of user preference model for hearing aids: We propose a user preference model that can be used to predict the likelihood of user preference deviation from their prescribed hearing aid configurations. v) Over-the-counter hearing aid preset development: Using a user preference model, we propose two different algorithms that can be used to derive limited discrete hearing aid configurations that cover a large population with hearing loss.