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 repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1910.11480")

Code

Syntology Ran 17 of 20 code samples harvested from 3 repositories linked to this paper; 3 have no recorded run. Of those that ran: 17 ran with no contract checked.

By repository: community (archive-listed): 19 samples from 3 repositories, 17 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Moon-sung-woo/ParallelWaveGan_korean mentioned on GitHubpytorchMIT report
TensorSpeech/TensorflowTTS mentioned on GitHubtf report
bigpon/QPPWG mentioned on GitHubpytorchMIT report
bigpon/vcc20_baseline_cyclevae mentioned on GitHubpytorchMIT report
coqui-ai/TTS mentioned on GitHubpytorchMPL-2.0 report
deciding/ParallelWaveGAN mentioned on GitHubpytorchMIT report
facebookresearch/denoiser mentioned on GitHubpytorch report
mukeshv0/ParallelWaveGAN mentioned on GitHubpytorchMIT report
yanggeng1995/FB-MelGAN mentioned on GitHubpytorch report
yanggeng1995/GAN-TTS mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

20 samples harvested; 17 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, 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 3 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

batch_f0 bigpon/QPPWG/qppwg/utils/features.py community (archive-listed) ran MIT (permissive) · 0ed54be0f7619aca · report
check_hdf5 bigpon/vcc20_baseline_cyclevae/baseline/src/utils/utils.py community (archive-listed) ran MIT (permissive) · 92d84700541a2536 · report
dilated_factor bigpon/QPPWG/qppwg/utils/features.py community (archive-listed) ran fingerprinted MIT (permissive) · 8cd88186efdab6e0 · report
find_files mukeshv0/ParallelWaveGAN/parallel_wavegan/utils/utils.py community (archive-listed) ran MIT (permissive) · 562a6efae0225990 · report
loss_vae_laplace bigpon/vcc20_baseline_cyclevae/baseline/src/nets/gru_vae.py community (archive-listed) ran MIT (permissive) · 04dd0d78b380bade · report
low_cut_filter bigpon/QPPWG/qppwg/bin/preprocess.py community (archive-listed) ran MIT (permissive) · bbf58066f7748c5a · report
low_cut_filter bigpon/QPPWG/qppwg/utils/filters.py community (archive-listed) ran MIT (permissive) · 44d3c0be62e4bbab · report
low_cut_filter bigpon/vcc20_baseline_cyclevae/baseline/src/bin/feature_extract.py community (archive-listed) ran MIT (permissive) · 354a3798e3217759 · report
low_pass_filter bigpon/QPPWG/qppwg/utils/filters.py community (archive-listed) ran fingerprinted MIT (permissive) · c28f03204eefdd29 · report
padding bigpon/vcc20_baseline_cyclevae/baseline/src/utils/dataset.py community (archive-listed) ran fingerprinted MIT (permissive) · 9164e9f0890be261 · report
path_replace bigpon/QPPWG/qppwg/bin/preprocess.py community (archive-listed) ran MIT (permissive) · a5d255facaefc424 · report
read_hdf5 bigpon/vcc20_baseline_cyclevae/baseline/src/utils/utils.py community (archive-listed) ran MIT (permissive) · c0be466d384f4bf1 · report
read_hdf5 mukeshv0/ParallelWaveGAN/parallel_wavegan/utils/utils.py community (archive-listed) ran MIT (permissive) · 4f86bc80523a92c1 · report
sampling_vae_laplace bigpon/vcc20_baseline_cyclevae/baseline/src/nets/gru_vae.py community (archive-listed) ran fingerprinted MIT (permissive) · b45003226b3b8d82 · report
shape_hdf5 bigpon/vcc20_baseline_cyclevae/baseline/src/utils/utils.py community (archive-listed) ran MIT (permissive) · d3302da55afa1057 · report
spk_division bigpon/QPPWG/qppwg/bin/preprocess.py community (archive-listed) ran MIT (permissive) · 102ba7c26e81660b · report
validate_length bigpon/QPPWG/qppwg/utils/features.py community (archive-listed) ran MIT (permissive) · a4fce818fed4b3c9 · report
sampling_vae_laplace_batch bigpon/vcc20_baseline_cyclevae/baseline/src/nets/gru_vae.py community (archive-listed) unverified MIT (permissive) · 6e0be223aee6ee4e · report
stft bigpon/QPPWG/qppwg/losses/stft_loss.py community (archive-listed) unverified MIT (permissive) · d014b1a7520bc12b · report
load_checkpoint identical code first harvested elsewhere 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