Adversarial Reweighting for Speaker Verification Fairness
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 speakers, with relative EER reductions of 7.7 For nationality subgroups, the proposed algorithm showed 1.04 speakers, 0.76 between gender groups was reduced from 0.70 deviation over nationality groups decreased from 0.21 to 0.19.
READ FULL TEXT