{
  "absUrl": "https://arxiv.org/abs/2609.05076",
  "arxivId": "2609.05076",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yao Guo"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Yang Ai"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Hui-Peng Du"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Xiao-Hang Jiang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Chen-Yuan Ning"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Zhen-Hua Ling"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.05076",
  "originalTitle": "Enhancing Neural Speech Coding with Semantic and Visual Cues",
  "pdfUrl": "https://arxiv.org/pdf/2609.05076.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}