Personalization and Smartphone Implementation of ADRO Hearing Aid Amplification by Bayesian Machine Learning

The amplification function of hearing aids is normally prescribed based on population-based prescriptions, often overlooking individual hearing needs. Previous studies have shown that personalization or individualization of prescriptive amplification can lead to improved hearing. This paper introduces a personalized amplification strategy that applies a Bayesian learning personalization algorithm to the Adaptive Dynamic Range Optimization (ADRO) prescription. The personalized ADRO amplification strategy is then implemented on a smartphone platform as an app that can be deployed in the field or in real-world audio environments. The results of hearing preference experiments from six participants with hearing loss are reported. The results, on average, indicate higher preference for the personalized ADRO relative to the standard ADRO prescription.