{
  "absUrl": "https://arxiv.org/abs/2610.19388v1",
  "arxivId": "2610.19388",
  "arxivVersion": 1,
  "arxivVersionedId": "2610.19388v1",
  "authors": [
    {
      "affiliations": [
        "Yonsei University"
      ],
      "name": "Sangmin Lee"
    },
    {
      "affiliations": [
        "McGill University",
        "Mila - Quebec AI Institute"
      ],
      "name": "Yejin Jeon"
    },
    {
      "affiliations": [
        "McGill University",
        "Mila - Quebec AI Institute"
      ],
      "name": "David Ifeoluwa Adelani"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2610.19388v1",
  "originalTitle": "ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies",
  "pdfUrl": "https://arxiv.org/pdf/2610.19388v1.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}