STOPA: A Database of Systematic VariaTion Of DeePfake Audio for Open-Set Source Tracing and Attribution

TL;DR

STOPA is a comprehensive, systematically varied dataset designed to improve deepfake speech source tracing by providing detailed metadata across multiple synthesis models and parameters, enhancing attribution accuracy.

Contribution

The paper introduces STOPA, a large-scale, systematically curated dataset with rich metadata for deepfake speech source tracing, addressing limitations of existing datasets.

Findings

Higher attribution accuracy with systematic variation

Enhanced forensic analysis capabilities

Broader coverage of generative factors

Abstract

A key research area in deepfake speech detection is source tracing - determining the origin of synthesised utterances. The approaches may involve identifying the acoustic model (AM), vocoder model (VM), or other generation-specific parameters. However, progress is limited by the lack of a dedicated, systematically curated dataset. To address this, we introduce STOPA, a systematically varied and metadata-rich dataset for deepfake speech source tracing, covering 8 AMs, 6 VMs, and diverse parameter settings across 700k samples from 13 distinct synthesisers. Unlike existing datasets, which often feature limited variation or sparse metadata, STOPA provides a systematically controlled framework covering a broader range of generative factors, such as the choice of the vocoder model, acoustic model, or pretrained weights, ensuring higher attribution reliability. This control improves attribution accuracy, aiding forensic analysis, deepfake detection, and generative model transparency.