We propose UnitSpeech, a speaker-adaptive speech synthesis method that
f...
In this paper, we investigate Unsupervised Episode Generation methods to...
Although Graph Neural Networks (GNNs) have been successful in node
class...
Molecular relational learning, whose goal is to learn the interaction
be...
The density of states (DOS) is a spectral property of materials, which
p...
We propose Guided-TTS 2, a diffusion-based generative model for high-qua...
Most neural text-to-speech (TTS) models require <speech, transcript> pai...
In this work, we present Facial Identity Controllable GAN (FICGAN) for n...
Non-autoregressive neural machine translation (NART) models suffer from ...
Denoising diffusion probabilistic models (DDPM) have shown remarkable
pe...
Normalizing flows (NFs) have become a prominent method for deep generati...
Recently, text-to-speech (TTS) models such as FastSpeech and ParaNet hav...
Most of modern text-to-speech architectures use a WaveNet vocoder for
sy...