An Adaptive Method for Target Curve Selection

TL;DR

This paper adapts the Interactive Differential Evolution algorithm for audio preference testing, enabling efficient identification of preferred headphone frequency responses through adaptive paired comparisons with untrained consumers.

Contribution

It introduces an adaptive method using IDE for audio preference elicitation, demonstrating its effectiveness in a new domain with real consumer data.

Findings

The method converges reliably in the audio domain.

It simplifies the process of extracting consumer preferences.

The algorithm performs well with untrained listeners.

Abstract

In this paper, we introduce an adaptation of the "Interactive Differential Evolution" (IDE) algorithm to the audio domain for the task of identifying the preferred over-the-ear headphone frequency response target among consumers. The method is based on data collection using an adaptive paired rating listening test paradigm (paired comparison with a scale). The IDE algorithm and its parameters are explained in detail. Additionally, data collected from three listening experiments with more than 20 consumers is presented, and the algorithm's performance in this untested domain is investigated on the basis of two convergence measures. The results indicate that this method can converge and may ease the task of 'extracting' frequency response preference from untrained consumers.