{
  "absUrl": "https://arxiv.org/abs/2610.11461v1",
  "arxivId": "2610.11461",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.11461v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Shiao Zhu"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Lianbo Liu"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Sizhen Lyu"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yuzhe Wang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Sheng Li"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Takahiro Shinozaki"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.11461v1",
  "originalTitle": "Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech",
  "pdfUrl": "https://arxiv.org/pdf/2610.11461v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}