Domain Adversarial Training for Mitigating Gender Bias in Speech-based Mental Health Detection

TL;DR

This paper introduces a domain adversarial training method to reduce gender bias in speech-based mental health detection models, significantly improving their fairness and accuracy across genders.

Contribution

It presents a novel domain adversarial training approach that explicitly considers gender differences, enhancing fairness in speech-based depression and PTSD detection models.

Findings

F1-score increased by up to 13.29 percentage points

Method effectively reduces gender bias in mental health detection

Improves overall detection performance on the E-DAIC dataset

Abstract

Speech-based AI models are emerging as powerful tools for detecting depression and the presence of Post-traumatic stress disorder (PTSD), offering a non-invasive and cost-effective way to assess mental health. However, these models often struggle with gender bias, which can lead to unfair and inaccurate predictions. In this study, our study addresses this issue by introducing a domain adversarial training approach that explicitly considers gender differences in speech-based depression and PTSD detection. Specifically, we treat different genders as distinct domains and integrate this information into a pretrained speech foundation model. We then validate its effectiveness on the E-DAIC dataset to assess its impact on performance. Experimental results show that our method notably improves detection performance, increasing the F1-score by up to 13.29 percentage points compared to the baseline. This highlights the importance of addressing demographic disparities in AI-driven mental health assessment.