Methods › Audio › Generative Audio Models › WaveGlow
WaveGlow
Introduced by Ryan Prenger et al. in WaveGlow: A Flow-based Generative Network for Speech Synthesis
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
WaveGlow is a flow-based generative model that generates audio by sampling from a distribution. Specifically samples are taken from a zero mean spherical Gaussian with the same number of dimensions as our desired output, and those samples are put through a series of layers that transforms the simple distribution to one which has the desired distribution.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1811.00002'). Repositories: 2 listed of 2 in the graph, strongest link: mentioned on GitHub. The lookup matched a paper by its title, arXiv:1811.00002, not a method entry. This answer is about arXiv:1811.00002, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1811.00002 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 2 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: 21 · with a code link: 7 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 21 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 21 of 21, 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.
-
Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approach 10 Sep 2024 · 0 repositories · arXiv:2409.13734
-
Code-Mixed Text to Speech Synthesis under Low-Resource Constraints 2 Dec 2023 · 0 repositories · arXiv:2312.01103
-
Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learning 2 Dec 2023 · 0 repositories · arXiv:2312.01107
-
Affective social anthropomorphic intelligent system 19 Apr 2023 · 0 repositories · arXiv:2304.11046
-
Adaptive re-calibration of channel-wise features for Adversarial Audio Classification 21 Oct 2022 · 0 repositories · arXiv:2210.11722
-
NatiQ: An End-to-end Text-to-Speech System for Arabic 15 Jun 2022 · 0 repositories · arXiv:2206.07373
-
FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesis 27 Sep 2021 · 0 repositories · arXiv:2109.13675
-
Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging 26 Jul 2021 · 1 repository · arXiv:2107.12051
-
A Flow-Based Neural Network for Time Domain Speech Enhancement 16 Jun 2021 · 0 repositories · arXiv:2106.09008
-
Low Bit-Rate Wideband Speech Coding: A Deep Generative Model based Approach 4 Feb 2021 · 0 repositories · arXiv:2102.02640
-
Text-to-speech for the hearing impaired 3 Dec 2020 · 0 repositories · arXiv:2012.02174
-
MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution 3 Dec 2020 · 3 repositories · arXiv:2012.01684
-
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)
-
A comparison of Vietnamese Statistical Parametric Speech Synthesis Systems 26 May 2020 · 0 repositories · arXiv:2005.12962
-
Probing the phonetic and phonological knowledge of tones in Mandarin TTS models 23 Dec 2019 · 1 repository · arXiv:1912.10915
-
WaveFlow: A Compact Flow-based Model for Raw Audio 3 Dec 2019 · 4 repositories · arXiv:1912.01219Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)
-
Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement 14 Nov 2019 · 0 repositories · arXiv:1911.06266
-
Transferring neural speech waveform synthesizers to musical instrument sounds generation 27 Oct 2019 · 0 repositories · arXiv:1910.12381
-
Parametric Resynthesis with neural vocoders 16 Jun 2019 · 1 repository · arXiv:1906.06762
-
WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation 5 Apr 2019 · 0 repositories · arXiv:1904.02892
-
WaveGlow: A Flow-based Generative Network for Speech Synthesis 31 Oct 2018 · 2 repositories · arXiv:1811.00002Syntology 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 23 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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