LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracing

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.

Key Contributions

• LJ-Spoof corpus: 3M+ utterances from one speaker across 30 TTS families, 500 generatively variant subsets, systematically varying vocoders, prosody, hyperparameters, codec resynthesis, and neural post-processing
• First single-speaker anti-spoofing corpus providing comprehensive generative variation (VocVar, GenVar, ReVoc, ReCod, FWVar) simultaneously, enabling controlled speaker-conditioned anti-spoofing research
• Dual-purpose resource: reference training corpus for building robust anti-spoofing models AND a benchmark evaluation suite for fine-grained synthesis source tracing

🛡️ Threat Analysis

Details

Similar Papers