Yongwei Li

fake audio detection (2) parameter estimation (1) optimal transport (1) self-supervised learning (1) speech synthesis (1) speech recognition (1) prompt engineering (1) unsupervised domain adaptation (1) deepfake detection (1) deep learning (1) speaker verification (1) counterfactual reasoning (1) sample weighting (1) intra-class variation (1) neural codec (1) text-to-audio generation (1) audio deepfake (1) speech emotion recognition (1) equal error rate (1) emotional speech (1)