Honglie Chen

visual speech recognition (2) semi-supervised learning (2) lip reading (2) contrastive learning (1) sound source localization (1) object detection (1) self-supervised learning (1) weakly supervised learning (1) automatic speech recognition (1) video analysis (1) sound localization (1) model pruning (1) noise robustness (1) synthetic datum (1) sparse training (1) audio-visual speech (1) hard sample mining (1) neural network sparsity (1) sparse network (1) neural vocoder (1)