Min-Jae Hwang

speech synthesis (6) neural vocoder (2) self-supervised learning (2) text-to-speech synthesis (2) variational autoencoder (2) waveform generation (2) noise modeling (1) language model (1) speech enhancement (1) support vector machine (1) generative model (1) deep learning (1) generative adversarial network (1) noise robustness (1) latent feature (1) speech-to-speech translation (1) generative pre-trained transformer (1) acoustic model (1) latent space embedding (1) prosody analysis (1)