Logo image
Synthetic Audio Forensics Evaluation (SAFE) Challenge
Preprint   Open access

Synthetic Audio Forensics Evaluation (SAFE) Challenge

Kirill Trapeznikov, Paul Cummer, Pranay Pherwani, Jai Aslam, Michael S Davinroy, Peter Bautista, Laura Cassani, Matthew Stamm and Jill Crisman
ArXiv.org
07 Oct 2025
url
https://doi.org/10.48550/arxiv.2510.03387View
Open

Abstract

Computer Science - Sound
The increasing realism of synthetic speech generated by advanced text-to-speech (TTS) models, coupled with post-processing and laundering techniques, presents a significant challenge for audio forensic detection. In this paper, we introduce the SAFE (Synthetic Audio Forensics Evaluation) Challenge, a fully blind evaluation framework designed to benchmark detection models across progressively harder scenarios: raw synthetic speech, processed audio (e.g., compression, resampling), and laundered audio intended to evade forensic analysis. The SAFE challenge consisted of a total of 90 hours of audio and 21,000 audio samples split across 21 different real sources and 17 different TTS models and 3 tasks. We present the challenge, evaluation design and tasks, dataset details, and initial insights into the strengths and limitations of current approaches, offering a foundation for advancing synthetic audio detection research. More information is available at https://stresearch.github.io/SAFE/https://stresearch.github.io/SAFE/.

Metrics

6 Record Views

Details

Logo image