ExpV2S: Zero-Shot Expressive Video-to-Speech Synthesis via Latent Diffusion Model.

@inproceedings{zhang-2026-expv2s, author = {Fang Zhang and Anqi Gou and Linli Xu}, editor = {Stevan Rudinac and Zi Huang and Marcel Worring and Lucia Vadicamo and Xirong Li and Pascal Mettes and Lizi Liao}, title = {{ExpV2S: Zero-Shot Expressive Video-to-Speech Synthesis via Latent Diffusion Model}}, booktitle = {{Proceedings of the 2026 International Conference on Multimedia Retrieval, ICMR 2026, Amsterdam, The Netherlands, June 16-19, 2026}}, pages = {855--864}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805622.3810884}, doi = {https://doi.org/10.1145/3805622.3810884} }