{
  "absUrl": "https://arxiv.org/abs/2610.01012v1",
  "arxivId": "2610.01012",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.01012v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Gunwoo Lee"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yoori Oh"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yoseob Han"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.01012v1",
  "originalTitle": "Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning",
  "pdfUrl": "https://arxiv.org/pdf/2610.01012v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}