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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 7 code samples harvested from 4 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 6 samples from 3 repositories, 5 ran (1 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

descriptinc/melgan-neurips officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
MattSegal/speech-enhancement mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation (arXiv:1806.03185; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
Mixergi/MelGAN mentioned on GitHubtfSyntology: not harvested report
Moon-sung-woo/ParallelWaveGan_korean mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech (arXiv:2005.05106; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
TensorSpeech/TensorflowTTS mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis (arXiv:2010.05646; that paper's own run record: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
adrienchaton/BERGAN mentioned on GitHubpytorchSyntology: not harvested report
avi33/universalmelgan mentioned on GitHubpytorchSyntology: not harvested report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
dathudeptrai/TensorflowTTS mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FastSpeech 2: Fast and High-Quality End-to-End Text to Speech (arXiv:2006.04558; that paper's own run record: 83 ran (of which 27 constructed an object rather than computing a result; 70 with no instrument failure: 9 honoured, 1 violated, 60 with no contract checked; 13 where Syntology's instrument failed) · 36 unverified); nothing checks that they implement this paper's method. report
deciding/ParallelWaveGAN mentioned on GitHubpytorchMITSyntology: not harvested report
jacksonkaunismaa/neural-music mentioned on GitHubpytorchSyntology: not harvested report
jaywalnut310/melgan-pytorch mentioned on GitHubpytorchSyntology: not harvested report
rishikksh20/VocGAN mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech (arXiv:2005.05106; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
rishikksh20/melgan mentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech (arXiv:2005.05106; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
rosinality/melgan-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
seungwonpark/melgan mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
yanggeng1995/FB-MelGAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech (arXiv:2005.05106; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
yanggeng1995/GAN-TTS mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
2023-MindSpore-1/ms-code-74 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleSpeech paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A³T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing (arXiv:2203.09690; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

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

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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

descriptinc/melgan-neurips official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
files_to_list in 7 papers mel2wav/dataset.py ran MIT (permissive) · 6e8184ff4faf3139 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-25
rosinality/melgan-pytorch community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
calc_padding melgan.py ran · violated contract fingerprinted MIT (permissive) · f1f581545c4a0ab0 · report fixture: signature kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned int · level recorded 2026-09-22
wnconv1d melgan.py ran · our draft was wrong MIT (permissive) · adbaa42086223bfc · report fixture: signature in_channel:int/0/int, out_channel:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, groups:int/0/int, act:str/0/str · returned Sequential · level recorded 2026-09-22
wnconvtranspose1d melgan.py ran · our draft was wrong MIT (permissive) · d7b8ead7dfdd315e · report fixture: signature in_channel:int/0/int, out_channel:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, act:str/0/str · returned Sequential · level recorded 2026-09-22
seungwonpark/melgan community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
dynamic_range_compression in 31 papers utils/audio_processing.py ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · 83e2c862f7374ac7 · report fixture: signature x:Tensor/2/float, C:int/0/int, clip_val:float/0/float · returned Tensor · level recorded 2026-09-22
griffin_lim in 16 papers utils/audio_processing.py ran · our draft was wrong BSD-3-Clause (permissive) · 9f9ec26d4cdfdf7d · report fixture: signature magnitudes:Tensor/3/float, stft_fn:STFT/0/?, n_iters:int/0/int · returned Tensor · level recorded 2026-09-22
yanggeng1995/GAN-TTS community (archive-listed) 1 sample, 0 ran · 1 unverified
load_checkpoint in 277 papers generate.py 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