Adversarial Training for Multi-domain Speaker Recognition

TL;DR

This paper introduces an adversarial training approach to improve multi-domain speaker recognition by creating domain-invariant and speaker-discriminative speech representations, effectively addressing domain mismatch and dataset variance issues.

Contribution

The study proposes a novel adversarial training method specifically designed for multi-domain speaker recognition, outperforming existing unsupervised domain adaptation techniques.

Findings

Effective in reducing multi-domain mismatch

Outperforms existing unsupervised domain adaptation methods

Produces robust speaker representations

Abstract

In real-life applications, the performance of speaker recognition systems always degrades when there is a mismatch between training and evaluation data. Many domain adaptation methods have been successfully used for eliminating the domain mismatches in speaker recognition. However, usually both training and evaluation data themselves can be composed of several subsets. These inner variances of each dataset can also be considered as different domains. Different distributed subsets in source or target domain dataset can also cause multi-domain mismatches, which are influential to speaker recognition performance. In this study, we propose to use adversarial training for multi-domain speaker recognition to solve the domain mismatch and the dataset variance problems. By adopting the proposed method, we are able to obtain both multi-domain-invariant and speaker-discriminative speech representations for speaker recognition. Experimental results on DAC13 dataset indicate that the proposed method is not only effective to solve the multi-domain mismatch problem, but also outperforms the compared unsupervised domain adaptation methods.