Chenxing Li

audio source separation (3) multimodal learning (2) signal-to-distortion ratio (2) multi-task learning (2) multimodal large language model (2) adversarial robustness (1) model architecture (1) catastrophic forgetting (1) cross-modal learning (1) convolutional neural network (1) benchmark evaluation (1) neural architecture search (1) visual grounding (1) semantic alignment (1) speech dereverberation (1) question answering (1) speech enhancement (1) semantic consistency (1) speech synthesis (1) zero-shot learning (1)