Shengchen Li

contrastive learning (1) few-shot learning (1) transfer learning (1) embedding space (1) machine translation (1) data augmentation (1) multimodal learning (1) image captioning (1) speaker verification (1) transductive inference (1) synthetic speech detection (1) visual feature (1) singing voice synthesis (1) audio captioning (1) pitch contour (1) feature space regularization (1) bioacoustic event detection (1) singing voice detection (1) polyphonic music (1) frame-level labeling (1)