Shengpeng Ji

speech synthesis (4) zero-shot learning (3) vector quantization (3) generative model (2) spoken dialogue (2) multimodal representation (2) speech generation (2) discrete representation (2) speaker cloning (2) speech language model (2) contrastive learning (2) multimodal learning (2) speech recognition (2) speech processing (2) spoken dialogue system (2) spoken dialogue model (2) reinforcement learning (1) voice conversion (1) feature alignment (1) self-supervised learning (1)