Evaluating Speech Enhancement Systems Through Listening Effort

TL;DR

This paper introduces a simple, robust method to evaluate speech intelligibility and listening effort simultaneously, facilitating easier assessment of speech enhancement systems across diverse conditions without extra burden on subjects.

Contribution

A novel, easy-to-implement method for assessing speech intelligibility and listening effort concurrently, validated across multiple studies and diverse experimental setups.

Findings

Method is robust across different studies and conditions

Trends in listening effort and intelligibility are consistent

Proposed method simplifies evaluation process

Abstract

Understanding degraded speech is demanding, requiring increased listening effort (LE). Evaluating processed and unprocessed speech with respect to LE can objectively indicate if speech enhancement systems benefit listeners. However, existing methods for measuring LE are complex and not widely applicable. In this study, we propose a simple method to evaluate speech intelligibility and LE simultaneously without additional strain on subjects or operators. We assess this method using results from two independent studies in Norway and Denmark, testing 76 (50+26) subjects across 9 (6+3) processing conditions. Despite differences in evaluation setups, subject recruitment, and processing systems, trends are strikingly similar, demonstrating the proposed method's robustness and ease of implementation into existing practices.