mlsanityData to 7 Oct 2026

Easy, Interpretable, Effective: openSMILE for voice deepfake detection

arXiv 2408.15775 ↗First posted 28 Aug 2024eess.AS cs.AI cs.SDcited by 5

Not on the map. Why?

Abstract (arXiv)

In this paper, we demonstrate that attacks in the latest ASVspoof5 dataset -- a de facto standard in the field of voice authenticity and deepfake detection -- can be identified with surprising accuracy using a small subset of very simplistic features. These are derived from the openSMILE library, and are scalar-valued, easy to compute, and human interpretable. For example, attack A10`s unvoiced segments have a mean length of 0.09 +- 0.02, while bona fide instances have a mean length of 0.18 +- 0.07. Using this feature alone, a threshold classifier achieves an Equal Error Rate (EER) of 10.3% for attack A10. Similarly, across all attacks, we achieve up to 0.8% EER, with an overall EER of 15.7 +- 6.0%. We explore the generalization capabilities of these features and find that some of them transfer effectively between attacks, primarily when the attacks originate from similar Text-to-Speech (TTS) architectures. This finding may indicate that voice anti-spoofing is, in part, a problem of identifying and remembering signatures or fingerprints of individual TTS systems. This allows to better understand anti-spoofing models and their challenges in real-world application.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

31 of 45 references.

References · 31

  1. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  3. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  4. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
  5. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  6. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  7. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 277
  8. 2020Glow-TTS: A Generative Flow for Text-to-Speech via Monotonic Alignment Searchcited by 269
  9. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 173
  10. 2020End-to-end anti-spoofing with RawNet2cited by 160
  11. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 157
  12. 2020FastPitch: Parallel Text-to-speech with Pitch Predictioncited by 150
19 more
  1. 2022Does Audio Deepfake Detection Generalize?cited by 129
  2. 2022ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wildcited by 118
  3. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 110
  4. 2021StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversioncited by 57
  5. 2023Audio Deepfake Detection: A Surveycited by 49
  6. 2021Investigating self-supervised front ends for speech spoofing countermeasurescited by 43
  7. 2021Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?cited by 36
  8. 2022The Vicomtech Audio Deepfake Detection System based on Wav2Vec2 for the 2022 ADD Challengecited by 33
  9. 2023Improved DeepFake Detection Using Whisper Featurescited by 28
  10. 2023Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifiercited by 26
  11. 2019Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separationcited by 22
  12. 2024A robust audio deepfake detection system via multi-view featurecited by 19
  13. 2022Low-Resource Multilingual and Zero-Shot Multispeaker TTScited by 15
  14. 2024Source Tracing of Audio Deepfake Systemscited by 14
  15. 2020An explainability study of the constant Q cepstral coefficient spoofing countermeasure for automatic speaker verificationcited by 13
  16. 2022Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Featurescited by 8
  17. 2022Attacker Attribution of Audio Deepfakescited by 6
  18. 2022Open Challenges in Synthetic Speech Detectioncited by 5
  19. 2024Listening Between the Lines: Synthetic Speech Detection Disregarding Verbal Contentcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Survey on AI-Generated Media Detection: From Non-MLLM to MLLMcited by 12
  2. 2026Automated Dysphagia Screening Using Noninvasive Neck Acoustic Sensingcited by 0
  3. 2026Towards Dys-XAI: Influence-Based Explanations for Dysarthria Severity Assessmentcited by 0
  4. 2026What You Train Is What You Get: Gender Bias, Training Composition, and Post-Hoc Mitigation in Audio Deepfake Detectioncited by 0
  5. 2026CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detectioncited by 0