XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association
This work addresses the challenge of associating faces with voices across different languages, which is important for applications like biometrics and multimedia analysis, but appears incremental as it builds on existing cross-modal alignment techniques.
The paper tackles the problem of cross-modal face-voice association by introducing XM-ALIGN, a framework that combines explicit and implicit alignment mechanisms, which significantly improves verification performance in both heard and unheard languages on the MAV-Celeb dataset.
This paper introduces our solution, XM-ALIGN (Unified Cross-Modal Embedding Alignment Framework), proposed for the FAME challenge at ICASSP 2026. Our framework combines explicit and implicit alignment mechanisms, significantly improving cross-modal verification performance in both "heard" and "unheard" languages. By extracting feature embeddings from both face and voice encoders and jointly optimizing them using a shared classifier, we employ mean squared error (MSE) as the embedding alignment loss to ensure tight alignment between modalities. Additionally, data augmentation strategies are applied during model training to enhance generalization. Experimental results show that our approach demonstrates superior performance on the MAV-Celeb dataset. The code will be released at https://github.com/PunkMale/XM-ALIGN.