Is It Still Fair? Investigating Gender Fairness in Cross-Corpus Speech Emotion Recognition
It addresses fairness issues in AI systems for speech emotion recognition, which is important for applications like virtual assistants, but is incremental as it builds on existing cross-corpus research.
The study investigated gender fairness in cross-corpus speech emotion recognition, finding that fairness does not generalize well across different datasets, with performance gaps of up to 15% between genders in some cases.
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.