{
  "absUrl": "https://arxiv.org/abs/2611.19030v1",
  "arxivId": "2611.19030",
  "arxivVersion": 1,
  "arxivVersionedId": "2611.19030v1",
  "authors": [
    {
      "affiliations": [
        "National Taiwan University"
      ],
      "name": "Yi-Cheng Lin"
    },
    {
      "affiliations": [
        "National Taiwan University"
      ],
      "name": "Jia-Kai Dong"
    },
    {
      "affiliations": [
        "National Taiwan University"
      ],
      "name": "Kuan-Yu Chen"
    },
    {
      "affiliations": [
        "National Taiwan University"
      ],
      "name": "Szu-Chi Chen"
    },
    {
      "affiliations": [
        "National Taiwan University"
      ],
      "name": "Jian-Jiun Ding"
    },
    {
      "affiliations": [
        "NVIDIA"
      ],
      "name": "Sung-Feng Huang"
    },
    {
      "affiliations": [
        "NVIDIA"
      ],
      "name": "Yusuke Hirota"
    },
    {
      "affiliations": [
        "National Taiwan University",
        "Artificial Intelligence Center of Research Excellence, National Taiwan University"
      ],
      "name": "Hung-yi Lee"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2611.19030v1",
  "originalTitle": "Beyond Controllability: Speaker Diversity in Instruction-Guided Text-to-Speech",
  "pdfUrl": "https://arxiv.org/pdf/2611.19030v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}
