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.
XM-ALIGN: Unified Cross-Modal Embedding Alignment for Face-Voice Association
The XM-ALIGN framework uses unified explicit and implicit alignment to improve cross-modal verification performance across languages by optimizing shared embeddings from face and voice encoders.
- Year
- 2025
- Venue
- arXiv 2025
- Authors
- 4
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2512.06757ARXIV-DEFAULT
- TL;DR
- Semantic Scholar