Xiaorui Wang

audio source separation (3) multi-task learning (2) transformer architecture (2) multimodal learning (2) signal-to-distortion ratio (2) image generation (1) few-shot learning (1) contrastive learning (1) speech recognition (1) spoken language understanding (1) data augmentation (1) cross-modal learning (1) channel attention (1) neural architecture search (1) web corpus (1) knowledge distillation (1) intent classification (1) language model alignment (1) visual grounding (1) feature extraction (1)