Tsun-An Hsieh

speech enhancement (3) wasserstein distance (1) one-shot learning (1) transformer architecture (1) representation learning (1) speech separation (1) self-supervised learning (1) speech processing (1) multimodal learning (1) speaker embedding (1) domain knowledge (1) generative adversarial network (1) perceptual metric (1) perceptual loss (1) speaker adaptation (1) speech quality (1) phonetic information (1) perceptual evaluation of speech quality (1) pesq score (1) objective metrics (1)