mlsanityData to 7 Oct 2026

EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition

arXiv 2506.04652 ↗First posted 5 Jun 2025eess.AS cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a large-scale comparison of 13 debiasing methods applied to multi-label SER. Our study encompasses techniques from pre-processing, regularization, adversarial learning, biased learners, and distributionally robust optimization. Experiments conducted on acted and naturalistic emotion datasets, using WavLM and XLSR representations, evaluate each method under conditions of gender imbalance. Our analysis quantifies the trade-offs between fairness and accuracy, identifying which approaches consistently reduce gender performance gaps without compromising overall model performance. The findings provide actionable insights for selecting effective debiasing strategies and highlight the impact of dataset distributions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 29 of its 55 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

29 of 55 references.

References · 29

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,358
  3. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  4. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  5. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  6. 2018Adversarial Removal of Demographic Attributes from Text Datacited by 166
  7. 2020Learning from Failure: Training Debiased Classifier from Biased Classifiercited by 133
  8. 2021Learning Debiased Representation via Disentangled Feature Augmentationcited by 116
  9. 2018Towards Robust and Privacy-preserving Text Representationscited by 75
  10. 2021Diverse Adversaries for Mitigating Bias in Trainingcited by 48
  11. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 38
  12. 2022BLIND: Bias Removal With No Demographicscited by 22
17 more
  1. 2024Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Modelscited by 20
  2. 2024Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognitioncited by 19
  3. 2024On the social bias of speech self-supervised modelscited by 16
  4. 2022Speech Emotion Recognition using Supervised Deep Recurrent System for Mental Health Monitoringcited by 15
  5. 2024Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Modelscited by 15
  6. 2023Exploring data augmentation in bias mitigation against non-native-accented speechcited by 11
  7. 2024EMO-SUPERB: An In-depth Look at Speech Emotion Recognitioncited by 10
  8. 2024Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selectioncited by 10
  9. 2022User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition in Federated Learningcited by 9
  10. 2023Soft-prompt Tuning for Large Language Models to Evaluate Biascited by 6
  11. 2024Beyond the binary: Limitations and possibilities of gender-related speech technology researchcited by 5
  12. 2025Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approachcited by 5
  13. 2023Signal Is Harder To Learn Than Bias: Debiasing with Focal Losscited by 3
  14. 2024MSP-Podcast SER Challenge 2024: L'antenne du Ventoux Multimodal Self-Supervised Learning for Speech Emotion Recognitioncited by 3
  15. 2024Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularizationcited by 3
  16. 2025Is It Still Fair? Investigating Gender Fairness in Cross-Corpus Speech Emotion Recognitioncited by 3
  17. 2024Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech Emotion Recognition System Performancecited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2026VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speechcited by 2
  2. 2025TAU: A Benchmark for Cultural Sound Understanding Beyond Semanticscited by 1
  3. 2025MI-Fuse: Label Fusion for Unsupervised Domain Adaptation with Closed-Source Large-Audio Language Modelcited by 0