Is It Still Fair? Investigating Gender Fairness in Cross-Corpus Speech Emotion Recognition

TL;DR

This paper investigates whether gender fairness in speech emotion recognition models generalizes across different datasets, highlighting the importance of fairness in transfer learning scenarios and proposing a combined fairness adaptation mechanism.

Contribution

It introduces the first analysis of gender fairness generalizability in cross-corpus SER and proposes a novel fairness adaptation approach for transfer learning.

Findings

Provides insights into gender fairness transferability across datasets

Highlights the distinction between model performance and fairness

Proposes a combined fairness adaptation mechanism for SER

Abstract

Speech emotion recognition (SER) is a vital component in various everyday applications. Cross-corpus SER models are increasingly recognized for their ability to generalize performance. However, concerns arise regarding fairness across demographics in diverse corpora. Existing fairness research often focuses solely on corpus-specific fairness, neglecting its generalizability in cross-corpus scenarios. Our study focuses on this underexplored area, examining the gender fairness generalizability in cross-corpus SER scenarios. We emphasize that the performance of cross-corpus SER models and their fairness are two distinct considerations. Moreover, we propose the approach of a combined fairness adaptation mechanism to enhance gender fairness in the SER transfer learning tasks by addressing both source and target genders. Our findings bring one of the first insights into the generalizability of gender fairness in cross-corpus SER systems.