A curated list of tools, papers, and resources related to audio deepfake detection, with a focus on fine-tuning deep learning models such as AASIST, RawNet2, and LCNN.
This repository is dedicated to showcasing practical and research-oriented resources for detecting audio deepfakes. If you would like to contribute, feel free to submit a pull request or open an issue.
- Datasets
- Competitions
- Tools
- Baseline Models
- Surveys and Reviews
- Recent Research Papers
- Notable Conference Papers
- ASVspoof 2015–2021: https://www.asvspoof.org/
- PartialSpoof: Dataset download
- WaveFake: Paper | Dataset
- In-the-Wild Deepfake Audio Dataset: Paper | Dataset
- ASVspoof Challenge Series: Official Website
- ASVspoof2021 Baseline Implementation
- RawNet2 Implementation (official)
- AASIST Implementation (official)
- AASIST: Spectro-temporal graph attention network for anti-spoofing.
- RawNet2: End-to-end deep model working directly on raw waveforms.
- LCNN: Lightweight CNN model using Max-Feature-Map activations.
- Cohen et al., “A Study on Data Augmentation in Voice Anti-Spoofing”, Ben Gurion University, 2022.
- Almutairi and Elgibreen, “A Review of Modern Audio Deepfake Detection Methods”, King Saud University, 2022.
- Khanjani et al., “Audio Deepfakes: A Survey”, University of Maryland, 2023.
- Khan et al., “Voice Spoofing Attacks and Countermeasures”, Oakland University, 2023.
- Dixit et al., “Review of Audio Deepfake Detection Techniques”, Panjab University, 2023.
- Yi et al., “Audio Deepfake Detection: A Survey”, CASIA, 2023.
-
Audio Deepfake Detection: A Survey
Authors: Jiangyan Yi, Chenglong Wang, Jianhua Tao, Xiaohui Zhang, Chu Yuan Zhang, Yan Zhao
Publication Year: 2023
Link to paper -
Audio Deepfakes: A Survey
Authors: Fariborz Taherkhani, Nasir Memon, Arun Ross
Publication Year: 2022
Link to paper -
Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Authors: Xinrui Yan, Jiangyan Yi, Jianhua Tao, Jie Chen
Publication Year: 2024
Link to paper -
Audio-deepfake detection: Adversarial attacks and countermeasures
Authors: Not specified
Publication Year: 2024
Link to paper -
Navigating the Soundscape of Deception: A Comprehensive Survey on Audio Deepfake Generation, Detection, and Future Horizons
Authors: Taiba Majid Wani, Syed Asif Ahmad Qadri, Farooq Ahmad Wani, Irene Amerini
Publication Year: 2024
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
WaveFake: A Data Set to Facilitate Audio Deepfake Detection
Authors: Not specified
Publication Year: 2021
Link to paper -
Audio Deepfake Detection
Authors: Not specified
Publication Year: Not specified
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper -
Audio Deepfake Detection: A Survey
Authors: Not specified
Publication Year: 2023
Link to paper
- Region-Based Optimization in Continual Learning for Audio Deepfake Detection paper
- Improving Generalization for AI-Synthesized Voice Detection paper
- What to remember: Self-adaptive continual learning for audio deepfake detection paper
- Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detectionpaper
- I Can Hear You: Selective Robust Training for Deepfake Audio Detection Accept! congratulations
- SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Toward Cutting-Edge Speech Generation Methods reject,pity
- Contrastive Learning from Synthetic Audio Doppelgängers augmentation paper, Accept
- SONICS: Synthetic Or Not - Identifying Counterfeit Songs. paper
interspeech website
- Anti-spoofing Ensembling Model: Dynamic Weight Allocation in Ensemble Models for Improved Voice Biometrics Security paper
- Spoof Diarization: ""What Spoofed When"" in Partially Spoofed Audio paper
- Spoofing Speech Detection by Modeling Local Spectro-Temporal and Long-term Dependency paper
- Improving Copy-Synthesis Anti-Spoofing Training Method with Rhythm and Speaker Perturbation paper
- Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection paper
- Source Tracing of Audio Deepfake Systems paper
- How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio? paper
- Revisiting and Improving Scoring Fusion for Spoofing-aware Speaker Verification Using Compositional Data Analysis paper
- SecureSpectra: Safeguarding Digital Identity from Deep Fake Threats via Intelligent Signatures paper
- Interpretable Temporal Class Activation Representation for Audio Spoofing Detection paper
- DGPN: A Dual Graph Prototypical Network for Few-Shot Speech Spoofing Algorithm Recognition paper
- CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems paper
- Spoofed Speech Detection with a Focus on Speaker Embedding paper
- Exploring Self-supervised Embeddings and Synthetic Data Augmentation for Robust Audio Deepfake Detection paper
- One-class learning with adaptive centroid shift for audio deepfake detection paper
- Towards generalisable and calibrated audio deepfake detection with self-supervised representations paper
- Singing Voice Graph Modeling for SingFake Detection paper
- Genuine-Focused Learning using Mask AutoEncoder for Generalized Fake Audio Detection paper
- Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanism paper
- To what extent can ASV systems naturally defend against spoofing attacks? paper
- Balance, Multiple Augmentation, and Re-synthesis: A Triad Training Strategy for Enhanced Audio Deepfake Detection paper
- Speech Formants Integration for Generalized Detection of Synthetic Speech Spoofing Attacks paper
- Adapter Learning from Pre-trained Model for Robust Spoof Speech Detection paper
- Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection paper
- Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio paper
- Frequency-mix Knowledge Distillation for Fake Speech Detection paper
- HarmoNet: Partial DeepFake Detection Network based on Multi-scale HarmoF0 Feature Fusion paper
- A New Approach to Voice Authenticity paper
- Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset paper
- Harder or Different? Understanding Generalization of Audio Deepfake Detection paper
- RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection paper
- Generalized Fake Audio Detection via Deep Stable Learning paper
- CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection paper
- FakeSound: Deepfake General Audio Detection paper
2023 papers
- Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms paper
- Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systems paper
- How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning paper
- Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model paper
- Towards single integrated spoofing-aware speaker verification embeddings paper
- DoubleDeceiver: Deceiving the Speaker Verification System Protected by Spoofing Countermeasures paper
- Speaker-Aware Anti-spoofing paper
- Range-Based Equal Error Rate for Spoof Localization paper
- A conformer-based classifier for variable-length utterance processing in anti-spoofing paper
- Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing paper
- Phase perturbation improves channel robustness for speech spoofing countermeasures paper
- Towards Attention-based Contrastive Learning for Audio Spoof Detection paper
- Synthetic Voice Spoofing Detection based on Feature Pyramid Conformer paper
- Robust audio anti-spoofing countermeasure with joint training of front-end and back-end models paper
ICASSP website
- Fooling the Forgers: A Multi-Stage Framework for Audio Deepfake Detection paper
- WaveSpect: A Hybrid Approach to Synthetic Audio Detection via Waveform and Spectrogram Analysis paper
- FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning paper
- LlamaPartialSpoof: An LLM-Driven Fake Speech Dataset Simulating Disinformation Generation paper
- What Affects the Performance of Fake Audio Detection? Analyzing Factors in a Continual Learning Setting paper
- Adversarial Training and Gradient Optimization for Partially Deepfake Audio Localization paper
- Leveraging Mixture of Experts for Improved Speech Deepfake Detection paper
- Freeze and Learn: Continual Learning with Selective Freezing for Speech Deepfake Detection paper
- Integrating Spectro-Temporal Cross Aggregation and Multi-Scale Dynamic Learning for Audio Deepfake Detection paper
- Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0 paper
- Easy, Interpretable, Effective: openSMILE for voice deepfake detection paper
- Robust Audio Deepfake Detection using Ensemble Confidence Calibration paper
- Generalize Audio Deepfake Algorithm Recognition via Attribution Enhancement paper
- From Voices to Beats: Enhancing Music Deepfake Detection by Identifying Forgeries in Background paper
- Wave-Spectrogram Cross-Modal Aggregation for Audio Deepfake Detection paper
- Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation paper
- SpecViT: A Custom Vision-Transformer based Approach for Audio Deepfake Detection paper
- Deepfake Detection of Singing Voices With Whisper Encodings paper
- Continual Unsupervised Domain Adaptation for Audio Deepfake Detection paper
- Audio Features Investigation for Singing Voice Deepfake Detection paper
- Investigating voiced and unvoiced regions of speech for audio deepfake detection paper
- What Does an Audio Deepfake Detector Focus on? A Study in the Time Domain paper
- PET: High-Frequency Temporal Self-Consistency Learning for Partially Deepfake Audio Localization paper
- GNCL: A Graph Neural Network with Consistency Loss for Segment-Level Spoofed Speech Detection paper
- Robust Spoof Speech Detection Based on Multi-Scale Feature Aggregation and Dynamic Convolution paper
- Can Large-Scale Vocoded Spoofed Data Improve Speech Spoofing Countermeasure with a Self-Supervised Front End? paper
- Frame-to-Utterance Convergence: A Spectra-Temporal Approach for Unified Spoofing Detection paper
- CPAUG: Refining Copy-Paste Augmentation for Speech Anti-Spoofing paper
- One-Class Knowledge Distillation for Spoofing Speech Detection paper
- An Efficient Temporary Deepfake Location Approach Based Embeddings for Partially Spoofed Audio Detection paper
- Selective Domain-Invariant Feature for Generalizable Deepfake Detection paper
- Multi-Scale Permutation Entropy for Audio Deepfake Detection paper
- A Green Learning Approach to Spoofed Speech Detection paper
- Spoofing Attack Augmentation: Can Differently-Trained Attack Models Improve Generalisation? paper
- Improving Short Utterance Anti-Spoofing with Aasist2 paper
- FSD: An Initial Chinese Dataset for Fake Song Detection paper
- A Robust Audio Deepfake Detection System via Multi-View Feature paper
- Audio Deepfake Detection With Self-Supervised Wavlm And Multi-Fusion Attentive Classifier paper
- Does Audio Deepfake Detection Rely on Artifacts? paper
- SingFake: Singing Voice Deepfake Detection paper
- VFD-Net: Vocoder Fingerprints Detection for Fake Audio paper
- HM-CONFORMER: A Conformer-Based Audio Deepfake Detection System with Hierarchical Pooling and Multi-Level Classification Token Aggregation Methods paper
- Learning From Yourself: A Self-Distillation Method for Fake Speech Detection paper
- Can spoofing countermeasure and speaker verification systems be jointly optimised?? paper
- Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders paper
- Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network paper
- Leveraging Positional-Related Local-Global Dependency for Synthetic Speech Detection paper
- Reliability Estimation for Synthetic Speech Detection paper
- Enhancing voice spoofing detection in noisy environments using frequency feature masking augmentation. paper
- Hierarchical multi-source cues fusion for mono-to-binaural based Audio Deepfake Detection. paper
- One-class network leveraging spectro-temporal features for generalized synthetic speech detection paper
TASLP website
- ASSD: An AI-Synthesized Speech Detection Scheme Using Whisper Feature and Types Classification paper
- The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio paper
- Generalizable Speech Spoofing Detection Against Silence Trimming With Data Augmentation and Multi-Task Meta-Learning paper
- Dual-Branch Knowledge Distillation for Noise-Robust Synthetic Speech Detection trash(this is personal)
- Compact Time-Domain Representation for Logical Access Spoofed Audio paper
- The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance paper
- ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild paper
- The Impact of Silence on Speech Anti-Spoofing paper
- Generalized Voice Spoofing Detection via Integral Knowledge Amalgamation paper
- Device Features Based on Linear Transformation With Parallel Training Data for Replay Speech Detection paper
- Robustness of Speech Spoofing Detectors Against Adversarial Post-Processing of Voice Conversion paper
- Modified Magnitude-Phase Spectrum Information for Spoofing Detection paper
- Optimizing Tandem Speaker Verification and Anti-Spoofing Systems paper
- FTDKD: Frequency-Time Domain Knowledge Distillation for Low-Quality Compressed Audio Deepfake Detection paper
TIFS website
- On Joint Optimization of Automatic Speaker Verification and Anti-Spoofing in the Embedding Space paper
- Domain Generalization via Aggregation and Separation for Audio Deepfake Detection paper
- Audio Multi-View Spoofing Detection Framework Based on Audio-Text-Emotion Correlations paper
SPL website
- One-Class Learning Towards Synthetic Voice Spoofing Detection paper
- Synthetic Speech Detection Based on Local Autoregression and Variance Statistics paper
- The Role of Long-Term Dependency in Synthetic Speech Detection paper
- Comparative Analysis of ASV Spoofing Countermeasures: Evaluating Res2Net-Based Approaches paper
- Discriminative Frequency Information Learning for End-to-End Speech Anti-Spoofing paper
- End-to-End Dual-Branch Network Towards Synthetic Speech Detection paper
- Towards End-to-End Synthetic Speech Detection paper
- Synthetic Speech Detection Based on the Temporal Consistency of Speaker Features paper
- Multi-Level Information Aggregation Based Graph Attention Networks Towards Fake Speech Detection paper
- Compressed Domain Invariant Adversarial Representation Learning for Robust Audio Deepfake Detection. paper
- Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localization paper
- Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier paper
- How to Boost Anti-Spoofing with X-Vectors paper
- Investigating Active-Learning-Based Training Data Selection for Speech Spoofing Countermeasure paper
- The Clever Hans Effect in Voice Spoofing Detection paper
- Fixing Domain Bias for Generalized Deepfake Detection paper
- Learning to Listen and Listening to Learn: Spoofed Audio Detection Through Linguistic Data Augmentation paper
- RawSpectrogram: On the Way to Effective Streaming Speech Anti-Spoofing paper
- Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation paper
- Experimental Case Study of Self-Supervised Learning for Voice Spoofing Detection paper
- Investigating Self-Supervised Front Ends for Speech Spoofing Countermeasures paper
- Investigating Active-Learning-Based Training Data Selection for Speech Spoofing Countermeasure paper
- SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection paper
- Audio Deepfake Detection with Self-Supervised XLS-R and SLS Classifier paper
- Your Out-of-Distribution Detection Method is Not Robust! paper code
- Watermarking for Out-of-distribution Detection paper code
This list is non-exhaustive and will be updated regularly as the field continues to evolve.