{
  "annotation_id": "fcddb933-f4ad-4e76-bb53-6f47404f64d4",
  "date_created": "2026-02-17T05:53:12.536000Z",
  "date_modified": "2026-02-17T05:53:12.536000Z",
  "file_hash": "3b65806b711cb38c2c55bc3cf9da8800d7e500a2fac37d7679a9012a9f4dcfcf",
  "private": false,
  "record": {
    "abstract": "Speaker-specific anti-spoofing and synthesis-source tracing are central challenges in audio anti-spoofing. Progress has been hampered by the lack of datasets that systematically vary model architectures, synthesis pipelines, and generative parameters. To address this gap, we introduce LJ-Spoof, a speaker-specific, generatively diverse corpus that systematically varies prosody, vocoders, generative hyperparameters, bona fide prompt sources, training regimes, and neural post-processing. The corpus spans one speakers-including studio-quality recordings-30 TTS families, 500 generatively variant subsets, 10 bona fide neural-processing variants, and more than 3 million utterances. This variation-dense design enables robust speaker-conditioned anti-spoofing and fine-grained synthesis-source tracing. We further position this dataset as both a practical reference training resource and a benchmark evaluation suite for anti-spoofing and source tracing.",
    "arxiv_id": "2601.07958",
    "authors": [
      "Surya Subramani",
      "Hashim Ali",
      "Hafiz Malik"
    ],
    "categories": [
      "cs.SD",
      "cs.AI",
      "eess.AS"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracing",
    "url": "https://arxiv.org/abs/2601.07958",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "c87a9eed-dc31-46b7-916f-be3fa82e609a",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}