Disentangling Age and Identity with a Mutual Information Minimization Approach for Cross-Age Speaker Verification

TL;DR

This paper introduces a novel disentangled representation learning framework for cross-age speaker verification that minimizes mutual information to produce age-invariant speaker embeddings, improving performance across age gaps.

Contribution

The paper presents a mutual information minimization approach to disentangle age and identity features, with an aging-aware loss function for better cross-age speaker verification.

Findings

Outperforms existing methods on Vox-CA cross-age test sets

Produces age-invariant speaker embeddings

Effective in handling large age gaps

Abstract

There has been an increasing research interest in cross-age speaker verification~(CASV). However, existing speaker verification systems perform poorly in CASV due to the great individual differences in voice caused by aging. In this paper, we propose a disentangled representation learning framework for CASV based on mutual information~(MI) minimization. In our method, a backbone model is trained to disentangle the identity- and age-related embeddings from speaker information, and an MI estimator is trained to minimize the correlation between age- and identity-related embeddings via MI minimization, resulting in age-invariant speaker embeddings. Furthermore, by using the age gaps between positive and negative samples, we propose an aging-aware MI minimization loss function that allows the backbone model to focus more on the vocal changes with large age gaps. Experimental results show that the proposed method outperforms other methods on multiple Cross-Age test sets of Vox-CA.