An Age-Agnostic System for Robust Speaker Verification

TL;DR

This paper introduces an age-agnostic speaker verification system that uses domain classification to create a unified, robust speaker embedding applicable to both children and adults, improving performance across age groups.

Contribution

The proposed system employs a domain classifier and embedding expansion to achieve robust, age-invariant speaker verification, addressing limitations of prior domain adaptation methods.

Findings

Effective in reducing performance gap between children's and adults' speaker verification

Demonstrated on OGI and VoxCeleb datasets with improved accuracy

Provides a foundation for inclusive, age-adaptive speaker verification systems

Abstract

In speaker verification (SV), the acoustic mismatch between children's and adults' speech leads to suboptimal performance when adult-trained SV systems are applied to children's speaker verification (C-SV). While domain adaptation techniques can enhance performance on C-SV tasks, they often do so at the expense of significant degradation in performance on adults' SV (A-SV) tasks. In this study, we propose an Age Agnostic Speaker Verification (AASV) system that achieves robust performance across both C-SV and A-SV tasks. Our approach employs a domain classifier to disentangle age-related attributes from speech and subsequently expands the embedding space using the extracted domain information, forming a unified speaker representation that is robust and highly discriminative across age groups. Experiments on the OGI and VoxCeleb datasets demonstrate the effectiveness of our approach in bridging SV performance disparities, laying the foundation for inclusive and age-adaptive SV systems.