WAVENEXT 2: CONVNEXT-BASED FAST NEURAL VOCODERS WITH RESIDUAL DENOISING AND SUB-MODELING FOR GAN AND DIFFUSION MODELS
Wangzixi Zhou, Takuma Okamoto, Sakriani Sakti, Hisashi Kawai
Abstract
Most neural vocoders are limited to one type: either GAN or diffusion-based. While state-of-the-art models like Vocos and WaveNeXt use powerful ConvNeXt-based generators, they have only been used in GAN frameworks and have limited performance in multi-speaker settings. Moreover, diffusion models, despite training faster than GANs, have slow CPU inference. In this paper, we introduce WaveNeXt 2, a unified ConvNeXt-based framework compatible with both GAN and diffusion vocoders. Its core innovation is residual denoising and sub-modeling, where each sub-model progressively refines the waveform. Experimental results in the multi-speaker dataset demonstrate the effectiveness of our approach: (1) GAN-WaveNeXt 2 is much faster than HiFi-GAN and WaveFit, and (2) Diff-WaveNeXt 2 also delivers much faster inference and competitive synthesis quality compared with FastDiff with 4 steps. The Diff-WaveNeXt 2 is very training-efficient, training in only 32 hours, making it ideal for resource-constrained applications.
BibTeX
@inproceedings{icassp2026_wavenext2convnex,
title = {WAVENEXT 2: CONVNEXT-BASED FAST NEURAL VOCODERS WITH RESIDUAL DENOISING AND SUB-MODELING FOR GAN AND DIFFUSION MODELS},
author = {Wangzixi Zhou and Takuma Okamoto and Sakriani Sakti and Hisashi Kawai},
booktitle = {ICASSP 2026},
year = {2026}
}