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.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1910.06711'). Repositories: 21 listed of 21 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:1910.06711, not a method entry. This answer is about arXiv:1910.06711, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1910.06711 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 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 (of 7 harvested samples) · 1 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 14 · with a code link: 10 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 14 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 14 of 14, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
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 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
SpeedySpeech: Efficient Neural Speech Synthesis 9 Aug 2020 · 3 repositories · arXiv:2008.03802Syntology official (archive's flag): 1 ran · 1 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; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
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 official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
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 official (archive's flag): 1 ran · 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 (of 7 harvested samples) · 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