{
  "absUrl": "https://arxiv.org/abs/2609.22452v1",
  "arxivId": "2609.22452",
  "arxivVersion": 1,
  "arxivVersionedId": "2609.22452v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Xize Cheng"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Wenxu Jia"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Chenyuhao Wen"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Dongjie Fu"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Zehan Wang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Xinyu Zhang"
    },
    {
      "affiliations": [
        "Zhejiang University"
      ],
      "name": "Tao Jin"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.22452v1",
  "originalTitle": "Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models",
  "pdfUrl": "https://arxiv.org/pdf/2609.22452v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}