LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracing
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917198520385536 |
|---|---|
| author | Subramani, Surya Ali, Hashim Malik, Hafiz |
| author_facet | Subramani, Surya Ali, Hashim Malik, Hafiz |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07958 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracing Subramani, Surya Ali, Hashim Malik, Hafiz Sound Artificial Intelligence Audio and Speech Processing 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. |
| title | LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracing |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.07958 |