Jinchuan Tian

automatic speech recognition (6) large language model (3) speech recognition (3) self-supervised learning (2) sequence-to-sequence model (2) zero-shot learning (2) foundation model (2) machine translation (2) speech synthesis (2) speech enhancement (2) weakly supervised learning (1) speech processing (1) multimodal learning (1) model architecture (1) question answering (1) domain adaptation (1) source separation (1) multitask learning (1) model adaptation (1) multilingual speech processing (1)