GitHub

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

In our recent paper, we propose VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech. Several recent end-to-end text-to-speech (TTS) models enabling single ...
GitHub

VGAELDA: a representation learning model based on variational inference and graph autoencoder for predicting lncRNA-disease associations

The code has been tested running under Python 3.7.4, with the following packages and their dependencies installed: ...
Frontiers

Large industrial load forecasting using a timemixer model with frequency-domain attention and multi-scale frequency-domain convolution

As illustrated in Figure 4c, this module deploys multiple heterogeneous predictors, each performing independent inference at its corresponding temporal scale. Subsequently, a fusion operator is ...