Zhiyuan Zhu

singing voice synthesis (5) speech synthesis (4) audio generation (3) generative model (3) contrastive learning (3) style transfer (2) flow matching (2) audio understanding (2) phoneme alignment (2) spatial audio (2) large language model (2) deep learning (2) augmented reality (2) virtual reality (2) neural network (2) speech analysis (1) speech enhancement (1) temporal reasoning (1) in-context learning (1) zero-shot learning (1)