Papers › MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis

8 Oct 2019NeurIPS 2019 12arXiv:1910.06711archive 2025-07-28

Kundan Kumar, Rithesh Kumar, Thibault de Boissiere, Lucas Gestin, Wei Zhen Teoh, Jose Sotelo, Alexandre de Brebisson, Yoshua Bengio, Aaron Courville

Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques. Subjective evaluation metric (Mean Opinion Score, or MOS) shows the effectiveness of the proposed approach for high quality mel-spectrogram inversion. To establish the generality of the proposed techniques, we show qualitative results of our model in speech synthesis, music domain translation and unconditional music synthesis. We evaluate the various components of the model through ablation studies and suggest a set of guidelines to design general purpose discriminators and generators for conditional sequence synthesis tasks. Our model is non-autoregressive, fully convolutional, with significantly fewer parameters than competing models and generalizes to unseen speakers for mel-spectrogram inversion. Our pytorch implementation runs at more than 100x faster than realtime on GTX 1080Ti GPU and more than 2x faster than real-time on CPU, without any hardware specific optimization tricks.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1910.06711")

Code

Syntology Ran 5 of 7 code samples harvested from 4 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · violated contract; 4 ran · our draft was wrong.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 6 samples from 3 repositories, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

21 repositories listed; official and paper-mentioned ones first.

descriptinc/melgan-neurips officialmentioned in papermentioned on GitHubpytorchMIT report
MattSegal/speech-enhancement mentioned on GitHubpytorch report
Mixergi/MelGAN mentioned on GitHubtf report
Moon-sung-woo/ParallelWaveGan_korean mentioned on GitHubpytorchMIT report
TensorSpeech/TensorflowTTS mentioned on GitHubtf report
adrienchaton/BERGAN mentioned on GitHubpytorch report
avi33/universalmelgan mentioned on GitHubpytorch report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0 report
dathudeptrai/TensorflowTTS mentioned on GitHubtf report
deciding/ParallelWaveGAN mentioned on GitHubpytorchMIT report
jacksonkaunismaa/neural-music mentioned on GitHubpytorch report
jaywalnut310/melgan-pytorch mentioned on GitHubpytorch report
rishikksh20/VocGAN mentioned on GitHubpytorchMIT report
rishikksh20/melgan mentioned on GitHubpytorchBSD-3-Clause report
rosinality/melgan-pytorch mentioned on GitHubpytorch report
seungwonpark/melgan mentioned on GitHubpytorch report
yanggeng1995/FB-MelGAN mentioned on GitHubpytorch report
yanggeng1995/GAN-TTS mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

7 samples harvested; 5 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
2unverified

Licence: 1 of the 7 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

files_to_list descriptinc/melgan-neurips/mel2wav/dataset.py official repository unverified MIT (permissive) · 6e8184ff4faf3139 · report
calc_padding rosinality/melgan-pytorch/melgan.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · f1f581545c4a0ab0 · report
dynamic_range_compression seungwonpark/melgan/utils/audio_processing.py community (archive-listed) ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 83e2c862f7374ac7 · report
griffin_lim seungwonpark/melgan/utils/audio_processing.py community (archive-listed) ran · our draft was wrong BSD-3-Clause (permissive) · 9f9ec26d4cdfdf7d · report
wnconv1d rosinality/melgan-pytorch/melgan.py community (archive-listed) ran · our draft was wrong MIT (permissive) · adbaa42086223bfc · report
wnconvtranspose1d rosinality/melgan-pytorch/melgan.py community (archive-listed) ran · our draft was wrong MIT (permissive) · d7b8ead7dfdd315e · report
load_checkpoint yanggeng1995/GAN-TTS/generate.py community (archive-listed) unverified no licence file found · pointer only · f443ef0155d2d898 · report

Tasks

Speech SynthesisTranslation

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: MelGAN

1x1 ConvolutionAdamAverage PoolingConvolutionDilated ConvolutionGAN Hinge LossGrouped ConvolutionLSTMMelGANMelGAN Residual BlockResidual ConnectionSigmoid ActivationTanh ActivationVQ-VAEWeight NormalizationWindow-based Discriminator

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