Kou Tanaka

voice conversion (6) speech synthesis (3) generative adversarial network (3) neural vocoder (2) knowledge distillation (2) hidden markov model (1) gaussian mixture model (1) diffusion model (1) convolutional neural network (1) disentangled representation (1) variational autoencoder (1) pre-trained model (1) one-step inference (1) residual network (1) lightweight model (1) text-to-speech synthesis (1) facial expression (1) speech representation (1) crossmodal learning (1) action unit (1)