Automatic volume settings for environment sensitive hearing aids

Abstract

A study was conducted to demonstrate the automatic adjustment of the hearing aid control settings to minimize the need for manual user interventions. The proposed system was based on computational intelligence tools, such as artificial neural networks and neurofuzzy systems. These systems had the ability to learn the dynamics of highly nonlinear system without the need for having specific knowledge of their mathematical models. These techniques were adopted to map the acoustic features to the desired volume setting of the hearing aid user. A multilayer perceptron (MLP) and an adaptive network-based fuzzy inference system (ANFIS) were analyzed as two computational intelligence tools on three simulated users. These simulated users were suffering from moderate, severe, and profound hearing losses.