Adversarial Reweighting for Speaker Verification Fairness

Abstract

We address performance fairness for speaker verification using the adversarial reweighting (ARW) method. ARW is reformulated for speaker verification with metric learning, and shown to improve results across different subgroups of gender and nationality, without requiring annotation of subgroups in the training data. An adversarial network learns a weight for each training sample in the batch so that the main learner is forced to focus on poorly performing instances. Using a min-max optimization algorithm, this method improves overall speaker verification fairness. We present three different ARWformulations: accumulated pairwise similarity, pseudo-labeling, and pairwise weighting, and measure their performance in terms of equal error rate (EER) on the VoxCeleb corpus. Results show that the pairwise weighting method can achieve 1.08% overall EER, 1.25% for male and 0.67% for female speakers, with relative EER reductions of 7.7%, 10.1% and 3.0%, respectively. For nationality subgroups, the proposed algorithm showed 1.04% EER for US speakers, 0.76% for UK speakers, and 1.22% for all others. The absolute EER gap between gender groups was reduced from 0.70% to 0.58%, while the standard deviation over nationality groups decreased from 0.21 to 0.19.

References in corpus (13)

• Prototypical Networks for Few-shot Learning
• VoxCeleb2: Deep Speaker Recognition
• VoxCeleb: a large-scale speaker identification dataset
• Attentive Statistics Pooling for Deep Speaker Embedding
• Fairness in Machine Learning: A Survey
• In defence of metric learning for speaker recognition
• Fairness Without Demographics in Repeated Loss Minimization
• Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020
• The Price of Fair PCA: One Extra Dimension
• Proxy Fairness
• What are the biases in my word embedding?
• Improving fairness in speaker verification via Group-adapted Fusion Network
• Model-Based Approach for Measuring the Fairness in ASR

Cited by in corpus (1)

• Study on the Fairness of Speaker Verification Systems on Underrepresented Accents in English