arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.08433cs.SDcs.CL
收藏

PLDA在说话人确认中的本地培训

Local Training for PLDA in Speaker Verification

Pachira(帕奇拉公司);Tsinghua University(清华大学)

Chenghui Zhao, Lantian Li, Dong Wang, April Pu

摘要:

PLDA是一种流行的i向量模型归一化方法,它在说话人确认中具有最先进的性能。然而,PLDA训练需要大量标记的开发数据,这在大多数情况下是非常昂贵的。缓解该问题的一种可能的方法是各种无监督自适应方法,其使用未标记的数据来使PLDA散射矩阵适应于目标域。在本文中,我们提出了一种新的“本地训练”的方法,利用不准确,但便宜得多的本地标签训练的PLDA模型。这些局部标签仅在单个转换内区分说话者,因此与正常的“全局标签”相比更容易获得。我们的实验表明,所提出的方法可以提供显着的性能改善,特别是有限的全球标记的数据。

英文摘要:

PLDA is a popular normalization approach for the i-vector model, and it has delivered state-of-the-art performance in speaker verification. However, PLDA training requires a large amount of labeled development data, which is highly expensive in most cases. A possible approach to mitigate the problem is various unsupervised adaptation methods, which use unlabeled data to adapt the PLDA scattering matrices to the target domain. In this paper, we present a new `local training' approach that utilizes inaccurate but much cheaper local labels to train the PLDA model. These local labels discriminate speakers within a single conversion only, and so are much easier to obtain compared to the normal `global labels'. Our experiments show that the proposed approach can deliver significant performance improvement, particularly with limited globally-labeled data.

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。

↑