{
  "absUrl": "https://arxiv.org/abs/2610.30477v1",
  "arxivId": "2610.30477",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.30477v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Yejin Jeon"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Luel Hagos Beyene"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Marie Maltais"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Hyounghun Kim"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "David Ifeoluwa Adelani"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.30477v1",
  "originalTitle": "EmoFI-TTS: Face-Conditioned Expressive Voice Synthesis with Intensity Modulation",
  "pdfUrl": "https://arxiv.org/pdf/2610.30477v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}