Ning Dong

speech translation (2) multi-task learning (1) variational inference (1) self-supervised learning (1) knowledge distillation (1) speech recognition (1) multilingual translation (1) neural machine translation (1) parallel corpus (1) automatic speech recognition (1) mutual information (1) latent variable model (1) cross-modal alignment (1) mixture of expert (1) model pre-training (1) modality fusion (1) evidence lower bound (1) speech-to-speech translation (1) posterior collapse (1) encoder-decoder model (1)