mlsanityData to 7 Oct 2026

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

arXiv 2505.19644 ↗First posted 26 May 2025cs.SD cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

25 of 42 references.

References · 25

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  5. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  6. 2020Unsupervised Cross-lingual Representation Learning for Speech Recognitioncited by 496
  7. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  8. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 337
  9. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  10. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
  11. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 150
  12. 2021Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Schemecited by 99
13 more
  1. 2020Unsupervised Speech Decomposition via Triple Information Bottleneckcited by 87
  2. 2021SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Modelcited by 56
  3. 2024MLAAD: The Multi-Language Audio Anti-Spoofing Datasetcited by 55
  4. 2022DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANscited by 43
  5. 2025ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speechcited by 25
  6. 2022TIMIT-TTS: a Text-to-Speech Dataset for Multimodal Synthetic Media Detectioncited by 16
  7. 2024Source Tracing of Audio Deepfake Systemscited by 14
  8. 2022An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audiocited by 12
  9. 2024Diffuse or Confuse: A Diffusion Deepfake Speech Datasetcited by 8
  10. 2023Distinguishing Neural Speech Synthesis Models Through Fingerprints in Speech Waveformscited by 6
  11. 2024Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategycited by 5
  12. 2022Transformer-Based Speech Synthesizer Attribution in an Open Set Scenariocited by 4
  13. 2024An Explainable Probabilistic Attribute Embedding Approach for Spoofed Speech Characterizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2026Open-Set Source Tracing as Compositional Factors via Structured Prototypescited by 1
  2. 2025Towards Reliable Audio Deepfake Attribution and Model Recognition: A Multi-Level Autoencoder-Based Frameworkcited by 0
  3. 2026LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracingcited by 0
  4. 2026SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detectioncited by 0
  5. 2026Ethical and Technical Limits of Deepfake Speech Datasetscited by 0
  6. 2026Clean Accuracy Does Not Guarantee Provenance Robustness: A Prospective Codec-Stress Evaluation of Audio Attributioncited by 0