SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluation

Linxi Li; Yuncong Yu; Qianwei Guo; Liwei Jin; Yechen Wang; Carsten Maple

SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluation

Sound 2026-07-06 v1 Artificial Intelligence

Authors: Linxi Li , Yuncong Yu , Qianwei Guo , Liwei Jin , Yechen Wang , Carsten Maple

Abstract

While audio deepfake detection has advanced significantly, representative detectors show limited generalization to synthetic sound effects. Existing environmental audio datasets such as EnvSDD provide important initial resources, but remain limited in scale and generation provenance for studying isolated sound-effect deepfakes. To support this direction, we present SynSFX, a large-scale corpus of 43374 clips (26452 synthetic, 16922 real) spanning 7 popular text-to-audio models.

Keywords

audio deepfake detection sound effects text-to-audio dataset synthetic audio

Cite

@article{arxiv.2607.04848,
  title  = {SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluation},
  author = {Linxi Li and Yuncong Yu and Qianwei Guo and Liwei Jin and Yechen Wang and Carsten Maple},
  journal= {arXiv preprint arXiv:2607.04848},
  year   = {2026}
}

Comments

7 pages, 1 figures