{
  "absUrl": "https://arxiv.org/abs/2611.19787v1",
  "arxivId": "2611.19787",
  "arxivVersion": 1,
  "arxivVersionedId": "2611.19787v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Jingbin Hu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Xinfa Zhu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Hao Wang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Wenjie Tian"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Kangxiang Xia"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Hangrui Hu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Kexin Huang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Jin Xu"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Liumeng Xue"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Lei Xie"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2611.19787v1",
  "originalTitle": "Rethinking Post-Training for Expressive Zero-Shot Text-to-Speech",
  "pdfUrl": "https://arxiv.org/pdf/2611.19787v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}
