mlsanityData to 7 Oct 2026

DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset

arXiv 2409.08731 ↗First posted 13 Sep 2024cs.SD eess.AScited by 20

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

Mainstream zero-shot TTS production systems like Voicebox and Seed-TTS achieve human parity speech by leveraging Flow-matching and Diffusion models, respectively. Unfortunately, human-level audio synthesis leads to identity misuse and information security issues. Currently, many antispoofing models have been developed against deepfake audio. However, the efficacy of current state-of-the-art anti-spoofing models in countering audio synthesized by diffusion and flowmatching based TTS systems remains unknown. In this paper, we proposed the Diffusion and Flow-matching based Audio Deepfake (DFADD) dataset. The DFADD dataset collected the deepfake audio based on advanced diffusion and flowmatching TTS models. Additionally, we reveal that current anti-spoofing models lack sufficient robustness against highly human-like audio generated by diffusion and flow-matching TTS systems. The proposed DFADD dataset addresses this gap and provides a valuable resource for developing more resilient anti-spoofing models.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 49 of its 58 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

49 of 58 references.

Closest ancestors · 17

Same direction, newest first

  1. 2024CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models31 Mar
  2. 2024NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models5 Mar
  3. 2024SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation24 Jan
  4. 2023DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation2 Oct
  5. 2023VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching10 Sep
  6. 2023Matcha-TTS: A fast TTS architecture with conditional flow matching6 Sep
  7. 2023DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training31 Jul
  8. 2023StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models13 Jun
  9. 2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers18 Apr
  10. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI23 Mar
  11. 2022ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech13 Jul
  12. 2022BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis25 Mar
5 more
  1. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidance23 Nov
  2. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior11 Jun
  3. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech13 May
  4. 2021Diff-TTS: A Denoising Diffusion Model for Text-to-Speech3 Apr
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesis21 Sep

Other references · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  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. 2019Heterogeneous Graph Attention Networkcited by 732
  6. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  7. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  8. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 487
  9. 2022UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022cited by 381
  10. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  11. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  12. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
20 more
  1. 2020End-to-end anti-spoofing with RawNet2cited by 160
  2. 2023Flow Matching in Latent Spacecited by 155
  3. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 150
  4. 2022Does Audio Deepfake Detection Generalize?cited by 129
  5. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 118
  6. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  7. 2017JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesiscited by 57
  8. 2021ASVspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speechcited by 56
  9. 2024MLAAD: The Multi-Language Audio Anti-Spoofing Datasetcited by 55
  10. 2024A Survey on Speech Deepfake Detectioncited by 26
  11. 2024Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detectioncited by 17
  12. 2022TIMIT-TTS: a Text-to-Speech Dataset for Multimodal Synthetic Media Detectioncited by 16
  13. 2024CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systemscited by 15
  14. 2020JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignmentcited by 13
  15. 2023Investigating Range-Equalizing Bias in Mean Opinion Score Ratings of Synthesized Speechcited by 13
  16. 2024Singing Voice Graph Modeling for SingFake Detectioncited by 9
  17. 2023The defender's perspective on automatic speaker verification: An overviewcited by 8
  18. 2024Neural Codec-based Adversarial Sample Detection for Speaker Verificationcited by 5
  19. 2022Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verificationcited by 2
  20. 2023An Initial Investigation of Neural Replay Simulator for Over-the-Air Adversarial Perturbations to Automatic Speaker Verificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 13.

20 papers.

Sort:

By area:

  1. 2025Speech DF Arena: A Leaderboard for Speech DeepFake Detection Modelscited by 20
  2. 2025Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternativecited by 6
  3. 2026Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTORcited by 4
  4. 2025Multi-level SSL Feature Gating for Audio Deepfake Detectioncited by 3
  5. 2025AUDDT: A Unified Benchmark Toolkit for Audio and Speech Deepfake Detectorscited by 2
  6. 2025Curved Worlds, Clear Boundaries: Generalizing Speech Deepfake Detection using Hyperbolic and Spherical Geometry Spacescited by 1
  7. 2026XLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detectioncited by 1
  8. 2026Alethia: A Foundational Encoder for Voice Deepfakescited by 1
  9. 2026Teffic-Audio: Tell Fact from Fictioncited by 1
  10. 2025Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge Systemcited by 0
  11. 2025AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worldscited by 0
  12. 2026LJ-Spoof: A Generatively Varied Corpus for Audio Anti-Spoofing and Synthesis Source Tracingcited by 0
8 more
  1. 2026A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detectioncited by 0
  2. 2026Probabilistic Verification of Voice Anti-Spoofing Modelscited by 0
  3. 2026Speaker-Invariant Representation Learning for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneckcited by 0
  4. 2026Ethical and Technical Limits of Deepfake Speech Datasetscited by 0
  5. 2026From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofingcited by 0
  6. 2026Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneckcited by 0
  7. 2026CoReLoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detectioncited by 0
  8. 2026Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffuse or Confuse: A Diffusion Deepfake Speech Dataset
  2. 2026Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning
  3. 2023Defending against Adversarial Audio via Diffusion Model
  4. 2025A Data-Driven Diffusion-based Approach for Audio Deepfake Explanations
  5. 2026Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception
  6. 2024GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis
  7. 2024The last Dance : Robust backdoor attack via diffusion models and bayesian approach
  8. 2026X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection