Yanzhi Tian

image translation (3) end-to-end model (2) neural machine translation (2) data augmentation (2) simultaneous translation (2) pre-trained model (1) end-to-end learning (1) model ensemble (1) speech-to-speech translation (1) sequence-to-sequence model (1) streaming translation (1) speech segmentation (1) regularized dropout (1) optical character recognition (1) text extraction (1) visual language (1) visual quality (1) prefix-to-prefix translation (1) image text recognition (1) feature extraction (1)