Yujun Wang

speech recognition (4) transfer learning (3) keyword spotting (3) model compression (3) self-supervised learning (2) text-to-speech synthesis (2) speaker adaptation (2) audio encoder (2) audio tagging (2) knowledge distillation (2) domain adaptation (1) speech synthesis (1) non-native speech (1) multimodal learning (1) contrastive learning (1) attention mechanism (1) few-shot learning (1) cross-modal retrieval (1) visual representation (1) model architecture (1)