Unsupervised Neural Adaptation Model Based on Optimal Transport for Spoken Language Identification
Unsupervised Neural Adaptation Model Based on Optimal Transport for Spoken Language Identification
复制标题
DOI：
10.1109/icassp39728.2021.9414045
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Xugang Lu;Peng Shen;Yu Tsao;H. Kawai
中科院分区：
文献类型：
--
作者：
Xugang Lu;Peng Shen;Yu Tsao;H. Kawai
由于训练集和测试集之间声学语音的统计分布的不匹配，口语识别（SLID）的性能会急剧下降。在本文中，我们提出了一个无监督的神经适应模型来处理SLID的分布失配问题。在我们的模型中，我们明确地制定了适应，以减少训练和测试数据集的特征和分类器的分布差异。此外，受最优运输（OT）的强大功能来衡量分布差异的启发，Wasserstein距离度量的适应损失。通过最小化训练数据集上的分类损失以及训练和测试数据集上的适应损失，减少了训练域和测试域之间的统计分布差异。我们在东方语言识别（OLR）挑战数据集上进行了SLID实验，其中训练和测试数据集是从不同的条件下收集的。我们的研究结果表明，跨领域测试任务取得了显着的改善。
Due to the mismatch of statistical distributions of acoustic speech between training and testing sets, the performance of spoken language identification (SLID) could be drastically degraded. In this paper, we propose an unsupervised neural adaptation model to deal with the distribution mismatch problem for SLID. In our model, we explicitly formulate the adaptation as to reduce the distribution discrepancy on both feature and classifier for training and testing data sets. Moreover, inspired by the strong power of the optimal transport (OT) to measure distribution discrepancy, a Wasserstein distance metric is designed in the adaptation loss. By minimizing the classification loss on the training data set with the adaptation loss on both training and testing data sets, the statistical distribution difference between training and testing domains is reduced. We carried out SLID experiments on the oriental language recognition (OLR) challenge data corpus where the training and testing data sets were collected from different conditions. Our results showed that significant improvements were achieved on the cross domain test tasks.