{
  "absUrl": "https://arxiv.org/abs/2609.09719",
  "arxivId": "2609.09719",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "Seoul National University",
        "University of California, Berkeley"
      ],
      "name": "Kang-wook Kim"
    },
    {
      "affiliations": [
        "Seoul National University"
      ],
      "name": "Jinyoung Park"
    },
    {
      "affiliations": [
        "Seoul National University",
        "KRAFTON"
      ],
      "name": "Jinsoo Kim"
    },
    {
      "affiliations": [
        "Seoul National University",
        "KRAFTON"
      ],
      "name": "Sehun Lee"
    },
    {
      "affiliations": [
        "Seoul National University",
        "Georgia Institute of Technology"
      ],
      "name": "Sang Hoon Woo"
    },
    {
      "affiliations": [
        "Seoul National University"
      ],
      "name": "Gunhee Kim"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.09719",
  "originalTitle": "StreamAlign: Streaming Text-Aligned Speech Tokenization",
  "pdfUrl": "https://arxiv.org/pdf/2609.09719.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}