@article{audiovisualcontrastivealignmentfordiffus,
  title = {Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement},
  author = {Colombe Mboungou and Mostafa Sadeghi and Jean-Eudes Ayilo and Romain Serizel},
  year = {2026},
  eprint = {2606.23712},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.23712},
}