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

TL;DR

This paper introduces an unsupervised neural adaptation approach using optimal transport to improve spoken language identification across different acoustic conditions, effectively reducing distribution mismatch.

Contribution

The proposed model uniquely applies Wasserstein distance-based adaptation to both features and classifiers for unsupervised domain adaptation in SLID.

Findings

Significant accuracy improvements on cross-domain SLID tasks.

Effective reduction of distribution discrepancy between training and testing data.

Demonstrated robustness across different language recognition conditions.

Abstract

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.