{
  "absUrl": "https://arxiv.org/abs/2609.32016v1",
  "arxivId": "2609.32016",
  "arxivVersion": 1,
  "arxivVersionedId": "2609.32016v1",
  "authors": [
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Christoph Schuhmann"
    },
    {
      "affiliations": [
        "LAION e.V. Scalable Learning & Multi-Purpose AI (SLAMPAI) Lab, Forschungszentrum Jülich GmbH"
      ],
      "name": "Robert Kaczmarczyk"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Gollam Rabby"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Felix Friedrich"
    },
    {
      "affiliations": [
        "L3S Research Center Black Forest Labs Computer Science Department, TU Darmstadt"
      ],
      "name": "Maurice Kraus"
    },
    {
      "affiliations": [
        "LAION e.V. Scalable Learning & Multi-Purpose AI (SLAMPAI) Lab, Forschungszentrum Jülich GmbH"
      ],
      "name": "Gijs Wijngaard"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Kourosh Nadi"
    },
    {
      "affiliations": [
        "机构信息未在 arXiv HTML 中可靠披露"
      ],
      "name": "Huu Nguyen"
    },
    {
      "affiliations": [
        "L3S Research Center Black Forest Labs Computer Science Department, TU Darmstadt",
        "Ontocord.AI German Research Center for Artificial Intelligence (DFKI)"
      ],
      "name": "Kristian Kersting"
    },
    {
      "affiliations": [
        "Hessian Center for AI (hessian.AI) Leibniz Universität Hannover"
      ],
      "name": "Sören Auer"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.32016v1",
  "originalTitle": "VoiceNet: Fine-Grained Voice Understanding Beyond Emotion at Scale",
  "pdfUrl": "https://arxiv.org/pdf/2609.32016v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}