Unsupervised neural adaptation model based on optimal transport for spoken language identification
This work tackles the problem of domain mismatch for spoken language identification systems, which is a common issue in real-world applications.
This paper addresses the performance degradation in spoken language identification (SLID) caused by mismatches in acoustic speech distributions between training and testing sets. The authors propose an unsupervised neural adaptation model that explicitly reduces distribution discrepancies on both feature and classifier levels, achieving significant improvements on cross-domain test tasks using the OLR challenge data corpus.
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.