Conditioning Trick for Training Stable GANs

no code implementations • 12 Oct 2020 • Mohammad Esmaeilpour, Raymel Alfonso Sallo, Olivier St-Georges, Patrick Cardinal, Alessandro Lameiras Koerich

In this paper we propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training.

Improving Stability of LS-GANs for Audio and Speech Signals

no code implementations • 12 Aug 2020 • Mohammad Esmaeilpour, Raymel Alfonso Sallo, Olivier St-Georges, Patrick Cardinal, Alessandro Lameiras Koerich

In this paper we address the instability issue of generative adversarial network (GAN) by proposing a new similarity metric in unitary space of Schur decomposition for 2D representations of audio and speech signals.

Generative Adversarial Network