@inproceedings{yeo-etal-2024-visual,
    title = "Where Visual Speech Meets Language: {VSP}-{LLM} Framework for Efficient and Context-Aware Visual Speech Processing",
    author = "Yeo, Jeonghun  and
      Han, Seunghee  and
      Kim, Minsu  and
      Ro, Yong Man",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-emnlp.666/",
    doi = "10.18653/v1/2024.findings-emnlp.666",
    pages = "11391--11406"
}