@misc{arxiv_2609_38440v1,
  title = {Monotonicity-Guided Semantic Alignment for Zero-shot Multispeaker Image-to-Speech Synthesis},
  author = {{Lijun Wang} and {Yixian Lu} and {Shogo Okada}},
  eprint = {2609.38440v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.38440v1}
}