Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator

arXiv:2403.16464v1 Announce Type: cross
Abstract: A generative adversarial network (GAN)-based vocoder trained with an adversarial discriminator is commonly used for speech synthesis because of its fast, lightweight, and high-quality characteristics. However, this data-driven model requires a large amount of training data incurring high data-collection costs. This fact motivates us to train a GAN-based vocoder on limited data. A promising solution is to augment the training data to avoid overfitting. However, a standard discriminator is unconditional and insensitive to distributional changes …

adversarial arxiv augmentation cs.lg cs.sd data eess.as generative generative adversarial network network training type