论文标题
最佳运输的部分耦合口语识别
Partial Coupling of Optimal Transport for Spoken Language Identification
论文作者
论文摘要
为了减少域差异以提高跨域口语识别（SLID）系统的性能，作为一种无监督的域适应方法（UDA）方法，我们提出了基于最佳运输（OT）的联合分布对准（JDA）模型。在培训和测试数据集之间，采用了基于OT的差异测量。在我们先前的研究中，据认为培训和测试集共享相同的标签空间。但是，在实际应用中，测试集的标签空间只是训练集的标签空间。完全匹配的训练和测试域进行分配对准可能会引入负域转移。在本文中，我们提出了一个基于部分最佳运输（POT）的JDA模型，即在JDA期间仅允许OT的部分耦合。此外，由于测试数据的标签尚不清楚，因此在锅中，基于运输成本的耦合上的软重量在域对齐期间是自适应设置的。对跨域滑动任务进行了实验，以评估所提出的UDA。结果表明，由于考虑了OT中的部分耦合，我们提出的UDA显着改善了性能。
In order to reduce domain discrepancy to improve the performance of cross-domain spoken language identification (SLID) system, as an unsupervised domain adaptation (UDA) method, we have proposed a joint distribution alignment (JDA) model based on optimal transport (OT). A discrepancy measurement based on OT was adopted for JDA between training and test data sets. In our previous study, it was supposed that the training and test sets share the same label space. However, in real applications, the label space of the test set is only a subset of that of the training set. Fully matching training and test domains for distribution alignment may introduce negative domain transfer. In this paper, we propose an JDA model based on partial optimal transport (POT), i.e., only partial couplings of OT are allowed during JDA. Moreover, since the label of test data is unknown, in the POT, a soft weighting on the coupling based on transport cost is adaptively set during domain alignment. Experiments were carried out on a cross-domain SLID task to evaluate the proposed UDA. Results showed that our proposed UDA significantly improved the performance due to the consideration of the partial couplings in OT.
