Conditioning Trick for Training Stable GANs

Abstract

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. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition. This binding makes the generator amenable to truncation and does not limit exploring all the possible modes. We slightly modify the BigGAN architecture incorporating residual network for synthesizing 2D representations of audio signals which enables reconstructing high quality sounds with some preserved phase information. Additionally, the proposed conditional training scenario makes a trade-off between fidelity and variety for the generated spectrograms. The experimental results on UrbanSound8k and ESC-50 environmental sound datasets and the Mozilla common voice dataset have shown that the proposed GAN configuration with the conditioning trick remarkably outperforms baseline architectures, according to three objective metrics: inception score, Frechet inception distance, and signal-to-noise ratio.

References in corpus (20)

• Conditional Generative Adversarial Nets
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Self-Attention Generative Adversarial Networks
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Which Training Methods for GANs do actually Converge?
• Adversarial Feature Learning
• Adversarially Learned Inference
• MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• Modulating early visual processing by language
• Mode Regularized Generative Adversarial Networks
• On Convergence and Stability of GANs
• Improving Generalization and Stability of Generative Adversarial Networks
• Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis
• Megapixel Size Image Creation using Generative Adversarial Networks
• The Stationary Phase Approximation, Time-Frequency Decomposition and Auditory Processing
• From Sound Representation to Model Robustness

Cited by in corpus (1)

• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets