{
  "absUrl": "https://arxiv.org/abs/2610.32042v1",
  "arxivId": "2610.32042",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.32042v1",
  "authors": [
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Jeongsoo Choi"
    },
    {
      "affiliations": [
        "Chung-Ang University"
      ],
      "name": "Ji-Hoon Kim"
    },
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Junseok Ahn"
    },
    {
      "affiliations": [
        "KAIST"
      ],
      "name": "Joon Son Chung"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.32042v1",
  "originalTitle": "X-Dubbing: Speech-to-Speech Translation under Temporal and Visual Constraints",
  "pdfUrl": "https://arxiv.org/pdf/2610.32042v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}