Disentangled representation learning for multilingual speaker recognition

TL;DR

This paper introduces a novel disentangled learning approach for multilingual speaker recognition, addressing the challenge of recognizing speakers across different languages by disentangling language information from speaker features.

Contribution

It presents a large-scale bilingual speaker evaluation set and a new disentanglement learning method combining adversarial and metric learning techniques without manual language labels.

Findings

Effective disentanglement of language and speaker features.

Improved recognition accuracy in bilingual scenarios.

A new evaluation benchmark for multilingual speaker recognition.

Abstract

The goal of this paper is to learn robust speaker representation for bilingual speaking scenario. The majority of the world's population speak at least two languages; however, most speaker recognition systems fail to recognise the same speaker when speaking in different languages. Popular speaker recognition evaluation sets do not consider the bilingual scenario, making it difficult to analyse the effect of bilingual speakers on speaker recognition performance. In this paper, we publish a large-scale evaluation set named VoxCeleb1-B derived from VoxCeleb that considers bilingual scenarios. We introduce an effective disentanglement learning strategy that combines adversarial and metric learning-based methods. This approach addresses the bilingual situation by disentangling language-related information from speaker representation while ensuring stable speaker representation learning. Our language-disentangled learning method only uses language pseudo-labels without manual information.