{
  "absUrl": "https://arxiv.org/abs/2610.21773v1",
  "arxivId": "2610.21773",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.21773v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Longjie Luo"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Zhongshu Hou"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Yuepeng Li"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Gang Yang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Shidong Shang"
    },
    {
      "affiliations": [
        "机构信息未能在本次解析中与作者逐人可靠绑定"
      ],
      "name": "Fan Zhou"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.21773v1",
  "originalTitle": "CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE Challenge",
  "pdfUrl": "https://arxiv.org/pdf/2610.21773v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}