#Adversarial Learning

Logo of vits
vits
Discover an innovative end-to-end TTS method that improves upon traditional two-stage systems using variational inference and adversarial learning. This approach enhances generative capabilities, resulting in natural-sounding speech. A stochastic duration predictor supports varied speech rhythms and tones from text. Human evaluations on the LJ Speech dataset demonstrate its superior performance, achieving MOS scores close to real human speech. Access the interactive demo for audio examples or explore available pretrained models.
Logo of neural-structured-learning
neural-structured-learning
Neural Structured Learning (NSL) in TensorFlow enhances neural network accuracy by using structured signals in training, benefiting particularly from limited labeled data. It provides flexible Keras APIs and TensorFlow operations for integrating graphs and adversarial perturbations. NSL is compatible with various network types like feed-forward, convolutional, and recurrent, and supports supervised and semi-supervised learning. It is easy to install via pip and works with TensorFlow 1.15+, excluding version 2.1. Explore available tutorials and research for more effective implementation.