Boquan Li

speaker recognition (2) metric learning (1) semi-supervised learning (1) self-supervised learning (1) multimodal learning (1) audio-visual learning (1) pseudo labeling (1) deepfake detection (1) speaker verification (1) masked prediction (1) pseudo label (1) audio-visual speech (1) face forgery detection (1) self-supervised representation (1) cross-dataset generalization (1) contrastive embedding (1) speech representation (1) equal error rate (1) intra-class compactness (1) inter-class discrepancy (1)