{
  "absUrl": "https://arxiv.org/abs/2610.19559v1",
  "arxivId": "2610.19559",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.19559v1",
  "authors": [
    {
      "affiliations": [
        "School of Artificial Intelligence and Computer Science, Shaanxi Normal University"
      ],
      "name": "Jing-Xuan Zhang"
    },
    {
      "affiliations": [
        "iFLYTEK Research, iFLYTEK Co., Ltd."
      ],
      "name": "Genshun Wan"
    },
    {
      "affiliations": [
        "iFLYTEK Research, iFLYTEK Co., Ltd."
      ],
      "name": "Jianqing Gao"
    },
    {
      "affiliations": [
        "iFLYTEK Research, iFLYTEK Co., Ltd."
      ],
      "name": "Jia Pan"
    },
    {
      "affiliations": [
        "School of Artificial Intelligence and Computer Science, Shaanxi Normal University",
        "Key Laboratory of Intelligent Computing and Service Technology for Folk SongMinistry of Culture and Tourism"
      ],
      "name": "Yumei Zhang"
    },
    {
      "affiliations": [
        "School of Artificial Intelligence and Computer Science, Shaanxi Normal University"
      ],
      "name": "Lichen Zhang"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.19559v1",
  "originalTitle": "Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling",
  "pdfUrl": "https://arxiv.org/pdf/2610.19559v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}