Year: 2026
Type: preprint
Abstract: We propose Relativistic Adversarial Feedback (RAF), a novel training objective for GAN vocoders that improves in-domain fidelity and generalization to unseen scenarios. Although modern GAN vocoders employ advanced architectures, their training objectives often fail to promote generalizable representations. RAF addresses this problem by leveraging speech self-supervised learning models to assist discriminators in evaluating sample quality, encouraging the generator to learn richer representations. Furthermore, we utilize relativistic pairing for real and fake waveforms to improve the modeling of the training data distribution. Experiments across multiple datasets show consistent gains in both objective and subjective metrics on GAN-based vocoders. Importantly, the RAF-trained BigVGAN-base outperforms the LSGAN-trained BigVGAN in perceptual quality using only 12\% of the parameters. Comparative studies further confirm the effectiveness of RAF as a training framework for GAN vocoders.
Source: arXiv (Cornell University)
Authors: Lee, Yongjoon, Choi, Jung-Woo
Institution: Korea Advanced Institute of Science and Technology
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7135241571
Cites:
Cited by:
Related to: