{
  "absUrl": "https://arxiv.org/abs/2609.06788",
  "arxivId": "2609.06788",
  "arxivVersion": null,
  "arxivVersionedId": null,
  "authors": [
    {
      "affiliations": [
        "Wenzhou-Kean University, Wenzhou, China"
      ],
      "name": "Bowen Yu"
    },
    {
      "affiliations": [
        "Wenzhou-Kean University, Wenzhou, China"
      ],
      "name": "Mingyu Huang"
    },
    {
      "affiliations": [
        "Wenzhou-Kean University, Wenzhou, China"
      ],
      "name": "Yishen Liu"
    },
    {
      "affiliations": [
        "Wenzhou-Kean University, Wenzhou, China"
      ],
      "name": "Yue Zhao"
    }
  ],
  "contract": "researcher-sidecars-v1",
  "id": "2609.06788",
  "originalTitle": "When Speech Meets Lips: Interpretable Audio-Visual Synchronization for L2 Pronunciation Assessment",
  "pdfUrl": "https://arxiv.org/pdf/2609.06788.pdf",
  "schemaVersion": 1,
  "type": "preprint"
}