@article{phonemelevelvisualspeechrecognitionviapo,
  title = {Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction},
  author = {Matthew Kit Khinn Teng and Haibo Zhang and Takeshi Saitoh},
  year = {2025},
  eprint = {2507.18863},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.18863},
}