Unsupervised neural adaptation model based on optimal transport for spoken language identification

by   Xugang Lu, et al.

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.


Partial Coupling of Optimal Transport for Spoken Language Identification

In order to reduce domain discrepancy to improve the performance of cros...

Cross-Domain Adaptation of Spoken Language Identification for Related Languages: The Curious Case of Slavic Languages

State-of-the-art spoken language identification (LID) systems, which are...

Statistical model-based evaluation of neural networks

Using a statistical model-based data generation, we develop an experimen...

Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models

Acoustic model adaptation to unseen test recordings aims to reduce the m...

Optimal Transport-based Adaptation in Dysarthric Speech Tasks

In many real-world applications, the mismatch between distributions of t...

Wasserstein Coresets for Lipschitz Costs

Sparsification is becoming more and more relevant with the proliferation...

Interpretable Dysarthric Speaker Adaptation based on Optimal-Transport

This work addresses the mismatch problem between the distribution of tra...