Performance Disparities between Accents in Automatic Speech Recognition (Student Abstract)

In this work, we expand the discussion of bias in Automatic Speech Recognition (ASR) through a large-scale audit. Using a large and global data set of speech, we perform an audit of some of the most popular English ASR services. We show that, even when controlling for multiple linguistic covariates, ASR service performance has a statistically significant relationship to the political alignment of the speaker's birth country with respect to the United States' geopolitical power.

Authors

• Alex DiChristofano Washington University, Saint Louis
• Henry Shuster Department of Computer Science & Engineering, Washington University in St. Louis
• Shefali Chandra Department of Women, Gender, and Sexuality Studies, Washington University in St. Louis Department of History, Washington University in St. Louis
• Neal Patwari Division of Computational & Data Sciences, Washington University in St. Louis Department of Computer Science & Engineering, Washington University in St. Louis Department of Electrical & Systems Engineering, Washington University in St. Louis

Keywords

• Accent
• Artificial Intelligence
• Audit
• Automatic Speech Recognition
• Bias
• Dialect
• English
• Fairness
• Language
• machine learning
• Natural Language Processing
• Speech