arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.04760eess.AScs.SD
收藏

面向说话人验证半监督域自适应的多目标渐进聚类

Multi-objective Progressive Clustering for Semi-supervised Domain Adaptation in Speaker Verification

Wuhan University(武汉大学);Duke Kunshan University(昆山杜克大学);Mashang Consumer Finance Co., Ltd(马上消费金融股份有限公司)

Ze Li, Yuke Lin, Ning Jiang, Xiaoyi Qin, Guoqing Zhao, Haiying Wu, Ming Li

AI总结:

针对说话人验证半监督域自适应的伪标记需求,提出多目标渐进聚类方法MoPC,结合多目标描述符、Infomap聚类及子中心纯化等策略优化伪标签,在VoxSRC 2023赛道3获第一,FFSVC数据集也表现良好。

摘要:

在说话人验证任务的半监督域自适应中,利用伪标记算法处理大规模无标注数据变得至关重要。本文提出了一种名为Multi-objective Progressive Clustering(MoPC,多目标渐进聚类)的新型伪标记方法,专为半监督域自适应设计。首先,我们利用目标域中有限的标注数据,基于图内去噪、类内去噪和类间去噪这三个不同的目标,推导域特定描述符。随后,采用Infomap算法进行嵌入聚类,并利用这些描述符进一步优化目标域的伪标签。此外,为进一步提升伪标签质量,我们引入了子中心纯化和渐进合并策略进行标签去噪。本文提出的MoPC方法在VoxSRC 2023赛道3的评估集上取得了4.95%的等错误率(EER),排名第一。我们还在FFSVC数据集上开展了额外实验,取得了可观的结果。

英文摘要:

Utilizing the pseudo-labeling algorithm with large-scale unlabeled data becomes crucial for semi-supervised domain adaptation in speaker verification tasks. In this paper, we propose a novel pseudo-labeling method named Multi-objective Progressive Clustering (MoPC), specifically designed for semi-supervised domain adaptation. Firstly, we utilize limited labeled data from the target domain to derive domain-specific descriptors based on multiple distinct objectives, namely within-graph denoising, intra-class denoising and inter-class denoising. Then, the Infomap algorithm is adopted for embedding clustering, and the descriptors are leveraged to further refine the target domain's pseudo-labels. Moreover, to further improve the quality of pseudo labels, we introduce the subcenter-purification and progressive-merging strategy for label denoising. Our proposed MoPC method achieves 4.95% EER and ranked the 1$^{st}$ place on the evaluation set of VoxSRC 2023 track 3. We also conduct additional experiments on the FFSVC dataset and yield promising results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑