Exploring Robust Face-Voice Matching in Multilingual Environments

TL;DR

This paper introduces a novel face-voice matching method for multilingual environments, utilizing a dual-branch structure, dynamic weighting, data augmentation, and score polarization to improve accuracy across diverse languages and conditions.

Contribution

It proposes a new face-voice association framework with four key components that enhance robustness and generalization in multilingual face-voice matching tasks.

Findings

Achieved EER of 20.07 on V2-EH dataset

Achieved EER of 21.76 on V1-EU dataset

Demonstrated significant effectiveness of the proposed methods

Abstract

This paper presents Team Xaiofei's innovative approach to exploring Face-Voice Association in Multilingual Environments (FAME) at ACM Multimedia 2024. We focus on the impact of different languages in face-voice matching by building upon Fusion and Orthogonal Projection (FOP), introducing four key components: a dual-branch structure, dynamic sample pair weighting, robust data augmentation, and score polarization strategy. Our dual-branch structure serves as an auxiliary mechanism to better integrate and provide more comprehensive information. We also introduce a dynamic weighting mechanism for various sample pairs to optimize learning. Data augmentation techniques are employed to enhance the model's generalization across diverse conditions. Additionally, score polarization strategy based on age and gender matching confidence clarifies and accentuates the final results. Our methods demonstrate significant effectiveness, achieving an equal error rate (EER) of 20.07 on the V2-EH dataset and 21.76 on the V1-EU dataset.