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

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.

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