Papers › Parallel WaveGAN: A fast waveform generation model based on generative adversarial...

Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram

25 Oct 2019arXiv:1910.11480archive 2025-07-28

Ryuichi Yamamoto, Eunwoo Song, Jae-Min Kim

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly optimizing multi-resolution spectrogram and adversarial loss functions, which can effectively capture the time-frequency distribution of the realistic speech waveform. As our method does not require density distillation used in the conventional teacher-student framework, the entire model can be easily trained. Furthermore, our model is able to generate high-fidelity speech even with its compact architecture. In particular, the proposed Parallel WaveGAN has only 1.44 M parameters and can generate 24 kHz speech waveform 28.68 times faster than real-time on a single GPU environment. Perceptual listening test results verify that our proposed method achieves 4.16 mean opinion score within a Transformer-based text-to-speech framework, which is comparative to the best distillation-based Parallel WaveNet system.

PaperPDFCodeCode 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 20 code samples harvested from 4 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 20 samples from 4 repositories, 17 ran (17 with no instrument failure; 0 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 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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
bigpon/QPPWG mentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report
bigpon/vcc20_baseline_cyclevae mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0Syntology: not harvested report
deciding/ParallelWaveGAN mentioned on GitHubpytorchMITSyntology: not harvested report
facebookresearch/denoiser mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Real Time Speech Enhancement in the Waveform Domain (arXiv:2006.12847; that paper's own run record: 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) · 1 unverified); nothing checks that they implement this paper's method. report
mukeshv0/ParallelWaveGAN mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 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
MindSpore-paper-code-2/code399 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

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

20 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

17ran
3unverified

Licence: 1 of the 20 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

bigpon/QPPWG community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
batch_f0 qppwg/utils/features.py ran MIT (permissive) · 0ed54be0f7619aca · report fixture: signature h:ndarray/2/float, f0_threshold:float/0/float, f0_cont:bool/0/bool, f0_idx:int/0/int, uv_idx:int/0/int · returned ndarray · level recorded 2026-09-24
dilated_factor qppwg/utils/features.py ran fingerprinted MIT (permissive) · 8cd88186efdab6e0 · report fixture: signature batch_f0:ndarray/1/float, fs:int/0/int, dense_factor:int/0/int · returned ndarray · level recorded 2026-09-24
low_cut_filter qppwg/bin/preprocess.py ran MIT (permissive) · bbf58066f7748c5a · report fixture: signature x:ndarray/1/float, fs:int/0/int, cutoff:int/0/int · returned ndarray · level recorded 2026-09-24
low_cut_filter qppwg/utils/filters.py ran MIT (permissive) · 44d3c0be62e4bbab · report fixture: signature x:ndarray/1/float, fs:int/0/int, cutoff:int/0/int · returned ndarray · level recorded 2026-09-24
low_pass_filter qppwg/utils/filters.py ran fingerprinted MIT (permissive) · c28f03204eefdd29 · report fixture: signature x:ndarray/1/float, fs:int/0/int, cutoff:float/0/float · returned ndarray · level recorded 2026-09-24
path_replace qppwg/bin/preprocess.py ran MIT (permissive) · a5d255facaefc424 · report fixture: signature filepath:str/0/str, inputpath:str/0/str, outputpath:str/0/str, extname:str/0/str · returned str · level recorded 2026-09-24
spk_division qppwg/bin/preprocess.py ran MIT (permissive) · 102ba7c26e81660b · report fixture: signature file_list:list/1/str, config:dict/0/?, spkinfo:dict/0/?, split:str/0/str, spkidx:int/0/int · returned tuple · level recorded 2026-09-24
validate_length qppwg/utils/features.py ran MIT (permissive) · a4fce818fed4b3c9 · report fixture: signature x:ndarray/1/float, y:ndarray/1/float, hop_size:NoneType/0/? · returned tuple · level recorded 2026-09-24
stft in 21 papers qppwg/losses/stft_loss.py unverified MIT (permissive) · d014b1a7520bc12b · report
bigpon/vcc20_baseline_cyclevae community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
check_hdf5 baseline/src/utils/utils.py ran fingerprinted MIT (permissive) · 92d84700541a2536 · report fixture: signature hdf5_name:str/0/str, hdf5_path:str/0/str · returned bool · level recorded 2026-09-24
loss_vae_laplace baseline/src/nets/gru_vae.py ran MIT (permissive) · 04dd0d78b380bade · report fixture: signature param:Tensor/2/float, clip:bool/0/bool, lat_dim:NoneType/0/? · returned Tensor · level recorded 2026-09-24
low_cut_filter baseline/src/bin/feature_extract.py ran MIT (permissive) · 354a3798e3217759 · report fixture: signature x:ndarray/1/float, fs:int/0/int, cutoff:int/0/int · returned ndarray · level recorded 2026-09-24
padding in 37 papers baseline/src/utils/dataset.py ran fingerprinted MIT (permissive) · 9164e9f0890be261 · report fixture: signature x:ndarray/2/float, flen:int/0/int, value:int/0/int · returned ndarray · level recorded 2026-09-24
read_hdf5 baseline/src/utils/utils.py ran MIT (permissive) · c0be466d384f4bf1 · report fixture: signature hdf5_name:str/0/str, hdf5_path:str/0/str · returned ndarray · level recorded 2026-09-24
sampling_vae_laplace baseline/src/nets/gru_vae.py ran fingerprinted MIT (permissive) · b45003226b3b8d82 · report fixture: signature param:Tensor/2/float, lat_dim:NoneType/0/? · returned Tensor · level recorded 2026-09-24
shape_hdf5 baseline/src/utils/utils.py ran MIT (permissive) · d3302da55afa1057 · report fixture: signature hdf5_name:str/0/str, hdf5_path:str/0/str · returned tuple · level recorded 2026-09-24
sampling_vae_laplace_batch baseline/src/nets/gru_vae.py unverified MIT (permissive) · 6e0be223aee6ee4e · report
mukeshv0/ParallelWaveGAN community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
find_files in 21 papers parallel_wavegan/utils/utils.py ran MIT (permissive) · 562a6efae0225990 · report fixture: signature root_dir:str/0/str, query:str/0/str, include_root_dir:bool/0/bool · returned list · level recorded 2026-09-24
read_hdf5 parallel_wavegan/utils/utils.py ran MIT (permissive) · 4f86bc80523a92c1 · report fixture: signature hdf5_name:str/0/str, hdf5_path:str/0/str · returned ndarray · level recorded 2026-09-24
yanggeng1995/GAN-TTS community (archive-listed) 1 sample, 0 ran · 1 unverified
load_checkpoint in 277 papers generate.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · f443ef0155d2d898 · report

Tasks

Speech SynthesisText to SpeechText-To-Speech Synthesistext-to-speech

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

ConvolutionDense ConnectionsDilated Causal ConvolutionDropoutMixture of Logistic DistributionsPhase ShuffleReLUTanh ActivationTestWGAN-GP LossWaveGANWaveNet

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