Xinyuan Qian

automatic speech recognition (3) multimodal learning (2) feature fusion (2) transformer architecture (2) sound source localization (2) talking face generation (1) attention mechanism (1) contrastive learning (1) length generalization (1) multi-modal learning (1) speech recognition (1) semantic representation (1) speech enhancement (1) human-robot interaction (1) audio-visual fusion (1) acoustic modeling (1) binary classifier (1) speech synthesis (1) video generation (1) federated learning (1)