ASVspoof-2019
Emerging15papers using it
2021first seen
ASVspoof 2019 is a dataset used to evaluate the effectiveness of algorithms in detecting spoofed speech, specifically focusing on deepfake audio generated by synthetic methods.
Papers using ASVspoof-2019 (15)
- Fusion of Modulation Spectrogram and SSL with Multi-head Attention for Fake Speech DetectionQuantizer-Aware Hierarchical Neural Codec Modeling for Speech Deepfake DetectionAmplifying Artifacts with Speech Enhancement in Voice Anti-spoofingATMM-SAGA: Alternating Training for Multi-Module with Score-Aware Gated Attention SASV systemComplementing Handcrafted Features with Raw Waveform Using a
Light-weight Auxiliary ModelDSVAE: Interpretable Disentangled Representation for Synthetic Speech
DetectionDeepfake Audio Detection Using Spectrogram-based Feature and Ensemble of
Deep Learning ModelsAudio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion
Attentive ClassifierCompression Robust Synthetic Speech Detection Using Patched Spectrogram
TransformerAttentive activation function for improving end-to-end spoofing
countermeasure systemsCharacterizing the temporal dynamics of universal speech representations
for generalizable deepfake detectionAdvanced Signal Analysis in Detecting Replay Attacks for Automatic Speaker Verification SystemsHeterogeneity over Homogeneity: Investigating Multilingual Speech
Pre-Trained Models for Detecting Audio DeepfakeMixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec
2.0DiffSSD: A Diffusion-Based Dataset For Speech Forensics