{
  "absUrl": "https://arxiv.org/abs/2609.08429",
  "arxivId": "2609.08429",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Lejun Min"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Junyu Dai"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Ruichen Zheng"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Xinyue Fan"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yang Xiang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Huaichen Zhang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Xingchen Song"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yufei Shi"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Han Zhao"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Xiangang Li"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.08429",
  "originalTitle": "Semantic Refinement of Universal Audio Representations through Audio-Description Alignment",
  "pdfUrl": "https://arxiv.org/pdf/2609.08429.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}