mlsanityData to 14 Oct 2026

EnvSDD: Benchmarking Environmental Sound Deepfake Detection

arXiv 2505.19203 ↗First posted 25 May 2025cs.SD cs.AI eess.AScited by 11

Not on the map. Why?

Abstract (arXiv)

Audio generation systems now create very realistic soundscapes that can enhance media production, but also pose potential risks. Several studies have examined deepfakes in speech or singing voice. However, environmental sounds have different characteristics, which may make methods for detecting speech and singing deepfakes less effective for real-world sounds. In addition, existing datasets for environmental sound deepfake detection are limited in scale and audio types. To address this gap, we introduce EnvSDD, the first large-scale curated dataset designed for this task, consisting of 45.25 hours of real and 316.74 hours of fake audio. The test set includes diverse conditions to evaluate the generalizability, such as unseen generation models and unseen datasets. We also propose an audio deepfake detection system, based on a pre-trained audio foundation model. Results on EnvSDD show that our proposed system outperforms the state-of-the-art systems from speech and singing domains.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 22 of its 32 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

22 of 32 references.

References · 22

  1. 2023Mistral 7Bcited by 3,164
  2. 2019Heterogeneous Graph Attention Networkcited by 734
  3. 2022Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentationcited by 719
  4. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  5. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 599
  6. 2022BEATs: Audio Pre-Training with Acoustic Tokenizerscited by 388
  7. 2019Clotho: An Audio Captioning Datasetcited by 358
  8. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 344
  9. 2022AudioGen: Textually Guided Audio Generationcited by 295
  10. 2022Masked Autoencoders that Listencited by 273
  11. 2021AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networkscited by 180
  12. 2020End-to-end anti-spoofing with RawNet2cited by 164
10 more
  1. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  2. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 117
  3. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 70
  4. 2024TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimizationcited by 68
  5. 2023Foley Sound Synthesis at the DCASE 2023 Challengecited by 19
  6. 2023The Ethical Implications of Generative Audio Models: A Systematic Literature Reviewcited by 18
  7. 2024SVDD 2024: The Inaugural Singing Voice Deepfake Detection Challengecited by 8
  8. 2022SceneFake: An Initial Dataset and Benchmarks for Scene Fake Audio Detectioncited by 5
  9. 2024FakeSound: Deepfake General Audio Detectioncited by 3
  10. 2024Detection of Deepfake Environmental Audiocited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 9.

11 papers.

  1. 2026Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learningcited by 6
  2. 2026Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTORcited by 4
  3. 2026AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plancited by 3
  4. 2025AUDDT: A Unified Benchmark Toolkit for Audio and Speech Deepfake Detectorscited by 2
  5. 2026AudioMosaic: Contrastive Masked Audio Representation Learningcited by 1
  6. 2025BEAT2AASIST model with layer fusion for ESDD 2026 Challengecited by 0
  7. 2026MoEScore: Mixture-of-Experts-Based Text-Audio Relevance Score Prediction for Text-to-Audio System Evaluationcited by 0
  8. 2026Environmental Sound Deepfake Detection Using Deep-Learning Frameworkcited by 0
  9. 2026SynSFX: Multi-Model Sound Effects Synthesis Dataset for Deepfake Detection and Evaluationcited by 0
  10. 2026MADBench: A Benchmark for Modality-Aware Audio Deepfake Detectioncited by 0
  11. 2026ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake Detectioncited by 0