Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
Journal
Interspeech 2025
Series/Report No.
Proceedings of the Annual Conference of the International Speech Communication Association Interspeech
Start Page
2053
End Page
2057
ISSN
2308457X
Date Issued
2025-08-17
Author(s)
Abstract
While subgroup disparities and performance bias are increasingly studied in computational research, fairness in categorical Speech Emotion Recognition (SER) remains underexplored. Existing methods often rely on explicit demographic labels, which are difficult to obtain due to privacy concerns. To address this limitation, we introduce an Implicit Demography Inference (IDI) module that leverages pseudo-labeling from a pre-trained model and unsupervised learning using k-means clustering to mitigate bias in SER. Our experiments show that pseudo-labeling IDI reduces subgroup disparities, improving fairness metrics by over 28% with less than a 2% decrease in SER accuracy. Also, the unsupervised IDI yields more than a 4.6% improvement in fairness metrics with a drop of less than 3.6% in SER performance. Further analyses reveal that the unsupervised IDI consistently mitigates race and age disparities, demonstrating its potential when explicit demographic information is unavailable.
Event(s)
26th Interspeech Conference 2025
Subjects
Bias
Fairness
Speech Emotion Recognition
Subgroup Disparities
SDGs
Publisher
ISCA
Type
conference paper