TL;DRJenGAN 是一种新的训练策略,通过堆叠位移的低通滤波器以确保位移等变性,从而提高非自回归基于 GAN 的神经声码器模型的性能并减少音调等人工痕迹。
Abstract
non-autoregressive gan-based neural vocoders are widely used due to their
fast inference speed and high perceptual quality. However, they often suffer
from audible artifacts such as tonal artifacts in their gener