Methods › Audio › Generative Audio Models › MelGAN
MelGAN
Introduced by Kundan Kumar et al. in MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
MelGAN is a non-autoregressive feed-forward convolutional architecture to perform audio waveform generation in a GAN setup. The architecture is a fully convolutional feed-forward network with mel-spectrogram s as input and raw waveform x as output. Since the mel-spectrogram is at a 256× lower temporal resolution, the authors use a stack of transposed convolutional layers to upsample the input sequence. Each transposed convolutional layer is followed by a stack of residual blocks with dilated convolutions. Unlike traditional GANs, the MelGAN generator does not use a global noise vector as input.
To deal with 'checkerboard artifacts' in audio, instead of using PhaseShuffle, MelGAN uses kernel-size as a multiple of stride.
Weight normalization is used for normalization. A window-based discriminator, similar to a PatchGAN is used for the discriminator.
Papers archive 2025-07-28
14 shown of 14, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis 20 Jun 2022 · 0 repositories · arXiv:2206.09920
-
cMelGAN: An Efficient Conditional Generative Model Based on Mel Spectrograms 15 May 2022 · 1 repository · arXiv:2205.07319
-
Real time spectrogram inversion on mobile phone 1 Mar 2022 · 1 repository · arXiv:2203.00756
-
Audio Deepfake Perceptions in College Going Populations 6 Dec 2021 · 0 repositories · arXiv:2112.03351
-
VocBench: A Neural Vocoder Benchmark for Speech Synthesis 6 Dec 2021 · 1 repository · arXiv:2112.03099
-
Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN 26 Mar 2021 · 0 repositories · arXiv:2103.14245
-
TFGAN: Time and Frequency Domain Based Generative Adversarial Network for High-fidelity Speech Synthesis 24 Nov 2020 · 1 repository · arXiv:2011.12206
-
Universal MelGAN: A Robust Neural Vocoder for High-Fidelity Waveform Generation in Multiple Domains 19 Nov 2020 · 2 repositories · arXiv:2011.09631
-
StyleMelGAN: An Efficient High-Fidelity Adversarial Vocoder with Temporal Adaptive Normalization 3 Nov 2020 · 2 repositories · arXiv:2011.01557Syntology ran 0 of 2 samples · 2 unverified
-
SpeedySpeech: Efficient Neural Speech Synthesis 9 Aug 2020 · 3 repositories · arXiv:2008.03802Syntology ran 1 of 1 samples · 0 unverified
-
VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network 30 Jul 2020 · 2 repositories · arXiv:2007.15256
-
Adversarial representation learning for private speech generation 16 Jun 2020 · 1 repository · arXiv:2006.09114Syntology ran 2 of 2 samples · 0 unverified
-
SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement 13 Jun 2020 · 0 repositories · arXiv:2006.07637
-
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis 8 Oct 2019 · 21 repositories · arXiv:1910.06711Syntology ran 5 of 7 samples · 2 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
16 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Speech Synthesis | 7 |
| CPU | 6 |
| GPU | 4 |
| Text to Speech | 2 |
| Vocal Bursts Intensity Prediction | 2 |
| text-to-speech | 2 |
| Audio Synthesis | 1 |
| BIG-bench Machine Learning | 1 |
| Face Swapping | 1 |
| Generative Adversarial Network | 1 |
| Music Generation | 1 |
| Privacy Preserving | 1 |
| Representation Learning | 1 |
| Spectral Reconstruction | 1 |
| Speech Enhancement | 1 |
| Translation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections