Recent studies have shown that pseudo labels can contribute to unsupervised domain adaptation (UDA) for speaker verification. Inspired by the self-training strategies that use an existing classifier to label the unlabeled data for retraining, we propose a cluster-guided UDA framework that labels the target domain data by clustering and combines the labeled source domain data and pseudo-labeled target domain data to train a speaker embedding network. To improve the cluster quality, we train a speaker embedding network dedicated for clustering by minimizing the contrastive center loss. The goal is to reduce the distance between an embedding and its assigned cluster center while enlarging the distance between the embedding and the other cluster centers. Using VoxCeleb2 as the source domain and CN-Celeb1 as the target domain, we demonstrate that the proposed method can achieve an equal error rate (EER) of 8.10% on the CN-Celeb1 evaluation set without using any labels from the target domain. This result outperforms the supervised baseline by 39.6% and is the state-of-the-art UDA performance on this corpus.

翻译：近期研究表明，伪标签有助于说话人验证中的无监督域适应（UDA，Unsupervised Domain Adaptation）。受利用现有分类器对未标注数据进行标注以重新训练的半监督训练策略启发，我们提出一种聚类引导的无监督域适应框架。该框架通过聚类对目标域数据进行标注，并联合标注的源域数据与伪标签化的目标域数据训练说话人嵌入网络。为提升聚类质量，我们通过最小化对比中心损失训练专用于聚类的说话人嵌入网络，旨在缩小嵌入向量与其分配聚类中心的距离，同时拉大嵌入向量与其他聚类中心的间距。以VoxCeleb2为源域、CN-Celeb1为目标域的实验表明，本方法在无需任何目标域标签的情况下，可在CN-Celeb1评估集上实现8.10%的等错误率（EER，Equal Error Rate），较有监督基线提升39.6%，并达到该语料库上最先进的无监督域适应性能。