Domain Adaptation and Autoencoder Based Unsupervised Speech Enhancement

TL;DR

This paper introduces a novel unsupervised speech enhancement method using domain adaptation with autoencoders, importance-weighting, and minimax techniques to improve performance across diverse datasets.

Contribution

It proposes a new domain adaptation approach for speech enhancement that transfers from larger, richer domains to smaller, limited ones, using variance constrained autoencoders and minimax training.

Findings

Outperforms state-of-the-art methods on VOICE BANK, IEEE, and TIMIT datasets.

Effectively reduces domain shift in unsupervised speech enhancement.

Demonstrates robustness across different languages, speakers, and environments.

Abstract

As a category of transfer learning, domain adaptation plays an important role in generalizing the model trained in one task and applying it to other similar tasks or settings. In speech enhancement, a well-trained acoustic model can be exploited to obtain the speech signal in the context of other languages, speakers, and environments. Recent domain adaptation research was developed more effectively with various neural networks and high-level abstract features. However, the related studies are more likely to transfer the well-trained model from a rich and more diverse domain to a limited and similar domain. Therefore, in this study, the domain adaptation method is proposed in unsupervised speech enhancement for the opposite circumstance that transferring to a larger and richer domain. On the one hand, the importance-weighting (IW) approach is exploited with a variance constrained autoencoder to reduce the shift of shared weights between the source and target domains. On the other hand, in order to train the classifier with the worst-case weights and minimize the risk, the minimax method is proposed. Both the proposed IW and minimax methods are evaluated from the VOICE BANK and IEEE datasets to the TIMIT dataset. The experiment results show that the proposed methods outperform the state-of-the-art approaches.