{
  "absUrl": "https://arxiv.org/abs/2609.14231",
  "arxivId": "2609.14231",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Ziyu Zhang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yun Chen"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Taihui Wang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Hanzhao Li"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Qicong Xie"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Rilin Chen"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Zhixian Zhao"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Lei Xie"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.14231",
  "originalTitle": "Modeling, Scaling, and Decoding: Optimizing Controllable Speech Generation with Nonverbal Vocalizations",
  "pdfUrl": "https://arxiv.org/pdf/2609.14231.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}