BriefGPT.xyz
Jun, 2024
JenGAN:基于GAN的语音合成中的堆叠偏移滤波器
JenGAN: Stacked Shifted Filters in GAN-Based Speech Synthesis
HTML
PDF
Hyunjae Cho, Junhyeok Lee, Wonbin Jung
TL;DR
JenGAN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
→