Preprint
Sep 2026
PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction
A vocoder is a pivotal component of modern text-to-speech (TTS) systems. Despite the significant progress of neural network-based vocoders, accurate phase reconstruction remains the main challenge limiting both audio quality and modeling efficiency. We introduce PhaseGAN, a lightweight vocoder that addresses this limit...
Wenzheng Zhang, Xue-Liang Zhang, Shu-Lin He et al.
· 0 citations