Minchuan Chen

generative adversarial network (2) neural vocoder (2) voice conversion (2) data augmentation (2) chinese spelling check (2) pre-trained language model (1) variational autoencoder (1) multi-task learning (1) speaker embedding (1) multi-modal learning (1) attention mechanism (1) word segmentation (1) self-attention network (1) parameter efficiency (1) singing voice synthesis (1) multimodal learning (1) text-to-speech synthesis (1) self-supervised learning (1) conditional generative adversarial network (1) semi-supervised learning (1)