# Evaluating and optimizing hearing-aid self-fitting methods using population coverage

## TL;DR

This paper introduces a new way to design self-fitting hearing aids by evaluating how well they meet the needs of a wide range of users.

## Contribution

A novel metric called population coverage is proposed to evaluate and optimize self-fitting hearing aid methods.

## Key findings

- The proposed metric estimates the fraction of users who can find a preferred configuration using self-fitting methods.
- Algorithms that maximize population coverage outperform clustering-based approaches in simulations.
- The tools can help reduce development costs by evaluating designs before user studies.

## Abstract

Adults with mild-to-moderate hearing loss can use over-the-counter hearing aids to treat their hearing loss at a fraction of traditional hearing care costs. These products incorporate self-fitting methods that allow end-users to configure their hearing aids without the help of an audiologist. A self-fitting method helps users configure the gain-frequency responses that control the amplification for each frequency band of the incoming sound. This paper considers how to guide the design of self-fitting methods by evaluating certain aspects of their design using computational tools before performing user studies. Most existing fitting methods provide various user interfaces to allow users to select a configuration from a predetermined set of presets. Accordingly, it is essential for the presets to meet the hearing needs of a large fraction of users who suffer from varying degrees of hearing loss and have unique hearing preferences. To this end, we propose a novel metric for evaluating the effectiveness of preset-based approaches by computing their population coverage. The population coverage estimates the fraction of users for which a self-fitting method can find a configuration they prefer. A unique aspect of our approach is a probabilistic model that captures how a user’s unique preferences differ from other users with similar hearing loss. Next, we propose methods for building preset-based and slider-based self-fitting methods that maximize the population coverage. Simulation results demonstrate that the proposed algorithms can effectively select a small number of presets that provide higher population coverage than clustering-based approaches. Moreover, we may use our algorithms to configure the number of increments of slider-based methods. We expect that the computational tools presented in this article will help reduce the cost of developing new self-fitting methods by allowing researchers to evaluate population coverage before performing user studies.