Methods › Audio › Generative Audio Models › MelGAN

MelGAN

14 papers tagged archive 2025-07-28

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.

PaperSource

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.

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.

TaskPapers
Speech Synthesis7
CPU6
GPU4
Text to Speech2
Vocal Bursts Intensity Prediction2
text-to-speech2
Audio Synthesis1
BIG-bench Machine Learning1
Face Swapping1
Generative Adversarial Network1
Music Generation1
Privacy Preserving1
Representation Learning1
Spectral Reconstruction1
Speech Enhancement1
Translation1

Usage over time archive 2025-07-28

Papers per year tagged with MelGAN: 2019 to 2022, peak 7 7 0 2019: 1 paper 2019 2020: 7 papers 2020 2021: 3 papers 2021 2022: 3 papers 2022
Papers per year the archive tags with this method, by the paper's archive date (14 dated). Bars are counts, not a trend claim.

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

Generative Audio Models

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