mlsanityData to 14 Oct 2026

SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis

arXiv 2508.07944 ↗First posted 11 Aug 2025cs.SD cs.AI cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

Despite growing attention to deepfake speech detection, the aspects of bias and fairness remain underexplored in the speech domain. To address this gap, we introduce the Speaker Characteristics Deepfake (SCDF) dataset: a novel, richly annotated resource enabling systematic evaluation of demographic biases in deepfake speech detection. SCDF contains over 237,000 utterances in a balanced representation of both male and female speakers spanning five languages and a wide age range. We evaluate several state-of-the-art detectors and show that speaker characteristics significantly influence detection performance, revealing disparities across sex, language, age, and synthesizer type. These findings highlight the need for bias-aware development and provide a foundation for building non-discriminatory deepfake detection systems aligned with ethical and regulatory standards.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 11 Aug 2025.

Builds on

19 of 27 references.

References · 19

  1. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  2. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
  3. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 361
  4. 2021A Survey on Neural Speech Synthesiscited by 184
  5. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  6. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 179
  7. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
  8. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  9. 2022ADD 2022: the First Audio Deep Synthesis Detection Challengecited by 96
  10. 2024ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scalecited by 91
  11. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  12. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
7 more
  1. 2024MLAAD: The Multi-Language Audio Anti-Spoofing Datasetcited by 56
  2. 2023DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversioncited by 38
  3. 2021An Examination of Fairness of AI Models for Deepfake Detectioncited by 35
  4. 2022GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detectioncited by 32
  5. 2024BUT Systems and Analyses for the ASVspoof 5 Challengecited by 12
  6. 2024Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluationscited by 8
  7. 2024Diffuse or Confuse: A Diffusion Deepfake Speech Datasetcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Evolutionary Multi-Objective Fusion of Deepfake Speech Detectorscited by 4
  2. 2026Ethical and Technical Limits of Deepfake Speech Datasetscited by 1
  3. 2026RAT: Reference-Augmented Training for ASV Anti-Spoofingcited by 0
  4. 2026What Do Deepfake Speech Detectors Actually Hear?cited by 0
  5. 2026What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detectioncited by 0
  6. 2026An Initial Study of Physiological Markers for Deepfake Speech Detectioncited by 0