ASVspoof 2021 LA

The 'ASVspoof 2021 LA' dataset is used to evaluate the performance of automatic speaker verification systems against spoofing attacks, specifically focusing on the detection of synthetic speech.

Papers using ASVspoof 2021 LA (8)

Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation2025 · 6 citesRawTFNet: A Lightweight CNN Architecture for Speech Anti-spoofing2025 · 2 citesXLSR-MamBo: Scaling the Hybrid Mamba-Attention Backbone for Audio Deepfake Detection2026XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection2024Investigating self-supervised front ends for speech spoofing countermeasures2021 · 12 citesGMM-ResNet2: Ensemble of Group ResNet Networks for Synthetic Speech Detection2024 · 9 citesAdvanced Signal Analysis in Detecting Replay Attacks for Automatic Speaker Verification Systems2024 · 1 citesAttentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection2024