Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across various recording environments. In this work, we present BigVGAN, a universal vocoder that generalizes well for various out-of-distribution scenarios without fine-tuning. We introduce periodic activation function and anti-aliased representation into the GAN generator, which brings the desired inductive bias for audio synthesis and significantly improves audio quality. In addition, we train our GAN vocoder at the largest scale up to 112M parameters, which is unprecedented in the literature. We identify and address the failure modes in large-scale GAN training for audio, while maintaining high-fidelity output without over-regularization. Our BigVGAN, trained only on clean speech (LibriTTS), achieves the state-of-the-art performance for various zero-shot (out-of-distribution) conditions, including unseen speakers, languages, recording environments, singing voices, music, and instrumental audio. We release our code and model at: https://github.com/NVIDIA/BigVGAN

翻译：尽管基于生成对抗网络（GAN）的声码器近期取得进展（模型基于声学特征生成原始波形），但在多种录音环境下为众多说话者合成高保真音频仍具挑战。本文提出BigVGAN——一种无需微调即可泛化至各类分布外场景的通用声码器。我们在GAN生成器中引入周期性激活函数与抗混叠表示，为音频合成提供所需归纳偏置，显著提升音频质量。此外，我们将GAN声码器训练规模扩展至空前的1.12亿参数，解决了大规模GAN音频训练中的失效模式，在避免过度正则化的同时保持高保真输出。仅基于干净语音（LibriTTS）训练的BigVGAN，在包括未见说话者、语言、录音环境、歌唱语音、音乐及乐器音频在内的多种零样本（分布外）条件下均达到最优性能。代码与模型已开源：https://github.com/NVIDIA/BigVGAN