Do face masks introduce bias in speech technologies? The case of automated scoring of speaking proficiency

TL;DR

This study investigates how face masks impact speech features and whether they introduce bias in automated English proficiency scoring, finding acoustic and speech pattern differences but no effect on scoring accuracy.

Contribution

It provides empirical evidence on the effects of face masks on speech assessment and shows that mask-induced changes do not bias scoring systems.

Findings

Acoustic measures differ between masked and unmasked speech.

Speech patterns show small but significant differences.

Scores remain unaffected by mask-related speech variations.

Abstract

The COVID-19 pandemic has led to a dramatic increase in the use of face masks worldwide. Face coverings can affect both acoustic properties of the signal as well as speech patterns and have unintended effects if the person wearing the mask attempts to use speech processing technologies. In this paper we explore the impact of wearing face masks on the automated assessment of English language proficiency. We use a dataset from a large-scale speaking test for which test-takers were required to wear face masks during the test administration, and we compare it to a matched control sample of test-takers who took the same test before the mask requirements were put in place. We find that the two samples differ across a range of acoustic measures and also show a small but significant difference in speech patterns. However, these differences do not lead to differences in human or automated scores of English language proficiency. Several measures of bias showed no differences in scores between the two groups.