Zeyu Xie

audio generation (2) transfer learning (1) speech synthesis (1) natural language generation (1) multimodal learning (1) cross-modal learning (1) deepfake detection (1) taxonomy construction (1) speech analysis (1) multimodal dataset (1) pre-trained model (1) audio captioning (1) sound event detection (1) temporal relation (1) large language model (1) binary classification (1) sound event (1)