# Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains

arXiv: https://arxiv.org/abs/2011.09631 · HTML: https://mlsanity.com/paper/2011.09631/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Fre-GAN: Adversarial Frequency-consistent Audio Synthesis](https://mlsanity.com/paper/2106.02297/) (2021)
- [GAN Vocoder: Multi-Resolution Discriminator Is All You Need](https://mlsanity.com/paper/2103.05236/) (2021)
- [Neural Synthesis of Footsteps Sound Effects with Generative Adversarial Networks](https://mlsanity.com/paper/2110.09605/) (2021)
- [AdaVocoder: Adaptive Vocoder for Custom Voice](https://mlsanity.com/paper/2203.09825/) (2022)
- [WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2206.09920/) (2022)
- [Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning](https://mlsanity.com/paper/2311.04313/) (2023)
- [BemaGANv2: Discriminator Combination Strategies for GAN-based Vocoders in Long-Term Audio Generation](https://mlsanity.com/paper/2506.09487/) (2025)

## Abstract (arXiv)

We propose Universal MelGAN, a vocoder that synthesizes high-fidelity speech in multiple domains. To preserve sound quality when the MelGAN-based structure is trained with a dataset of hundreds of speakers, we added multi-resolution spectrogram discriminators to sharpen the spectral resolution of the generated waveforms. This enables the model to generate realistic waveforms of multi-speakers, by alleviating the over-smoothing problem in the high frequency band of the large footprint model. Our structure generates signals close to ground-truth data without reducing the inference speed, by discriminating the waveform and spectrogram during training. The model achieved the best mean opinion score (MOS) in most scenarios using ground-truth mel-spectrogram as an input. Especially, it showed superior performance in unseen domains with regard of speaker, emotion, and language. Moreover, in a multi-speaker text-to-speech scenario using mel-spectrogram generated by a transformer model, it synthesized high-fidelity speech of 4.22 MOS. These results, achieved without external domain information, highlight the potential of the proposed model as a universal vocoder.