论文标题
对抗者的对手重新释放演讲者验证公平性
Adversarial Reweighting for Speaker Verification Fairness
论文作者
论文摘要
我们使用对抗性重新加权（ARW）方法来解决扬声器验证的性能公平性。 ARW已通过度量学习进行了重新审核，并显示出可以改善性别和国籍不同亚组的结果，而无需在培训数据中对子组的注释。对手网络在批处理中学习每个培训样本的重量，以便主要学习者被迫专注于表现不佳的实例。使用Min-Max优化算法，此方法可改善总体说话者的验证公平性。我们提出了三种不同的杂志：累积的成对相似性，伪标记和成对的加权，并根据Voxceleb语料库的同等错误率（EER）来衡量其性能。结果表明，成对的加权方法可以达到1.08％的总体EER，男性为1.25％，女性说话者为0.67％，相对EER降低分别为7.7％，10.1％和3.0％。对于国籍亚组，该拟议的算法显示，美国发言人的EER为1.04％，英国发言人为0.76％，其他所有其他人则为1.22％。性别群体之间的绝对EER差距从0.70％降低到0.58％，而国籍群的标准偏差从0.21降低到0.19。
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.
