There are two types of methods for non-autoregressive text-to-speech mod...
Various applications of voice synthesis have been developed independentl...
Neural vocoders based on the generative adversarial neural network (GAN)...
This paper proposes a hierarchical and multi-scale variational
autoencod...
Recent advances in neural multi-speaker text-to-speech (TTS) models have...
We present a novel high-fidelity real-time neural vocoder called VocGAN....