{
  "absUrl": "https://arxiv.org/abs/2609.30774v1",
  "arxivId": "2609.30774",
  "arxivVersion": 1,
  "arxivVersionedId": "2609.30774v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Shuhan Zhang"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Wenxuan Wu"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Haizhou Li"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.30774v1",
  "originalTitle": "Dialogue-Based Streaming Audio-Visual Target Speaker Extraction with Predictive Dialogue Information",
  "pdfUrl": "https://arxiv.org/pdf/2609.30774v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}