Yonghe Wang

speech translation (3) phrase break prediction (2) transfer learning (1) sequence labeling (1) knowledge distillation (1) multilingual translation (1) neural architecture search (1) parameter sharing (1) long short-term memory (1) pre-trained model (1) parameter-efficient fine-tuning (1) linear layer (1) knowledge preservation (1) multilingual speech translation (1) pluggable module (1) model retraining (1) morphological embedding (1) subword embedding (1) neural network (1) 1-bit quantization (1)