PhaseGAN: High-Fidelity Vocoder via Decoupled Amplitude and GAN-Driven Phase Reconstruction

2026-09-11

AI Summary

PhaseGAN通过解耦幅度和基于GAN的相位重建方法，解决了神经网络声码器中准确相位重建的问题，提高了音频质量和建模效率。

Abstract

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 limitation through a "mel $\rightarrow$ Amplitude $\rightarrow$ Phase" reconstruction pipeline. By reconstructing amplitude and phase spectra via distinct methodologies, the proposed PhaseGAN outperforms state-of-the-art baselines while utilizing fewer model parameters and reduced computational requirements. The compact version generates high-fidelity audio with approximately 500K parameters and 1 GMAC computational load, making it highly suitable for real-time applications on edge devices. In addition, our approach exhibits exceptional musical audio synthesis capabilities despite no training on musical data, illustrating unprecedented cross-domain generalization. See https://github.com/phasegan/phasegan-audio-demo for demos of our work.

Problem

• vocoder
• phase reconstruction
• audio quality
• modeling efficiency

Innovation

• PhaseGAN
• decoupled amplitude and phase reconstruction
• lightweight vocoder
• high-fidelity audio
• cross-domain generalization