Papers › ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech

ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech

19 Jul 2018ICLR 2019 5arXiv:1807.07281archive 2025-07-28

Wei Ping, Kainan Peng, Jitong Chen

In this work, we propose a new solution for parallel wave generation by WaveNet. In contrast to parallel WaveNet (van den Oord et al., 2018), we distill a Gaussian inverse autoregressive flow from the autoregressive WaveNet by minimizing a regularized KL divergence between their highly-peaked output distributions. Our method computes the KL divergence in closed-form, which simplifies the training algorithm and provides very efficient distillation. In addition, we introduce the first text-to-wave neural architecture for speech synthesis, which is fully convolutional and enables fast end-to-end training from scratch. It significantly outperforms the previous pipeline that connects a text-to-spectrogram model to a separately trained WaveNet (Ping et al., 2018). We also successfully distill a parallel waveform synthesizer conditioned on the hidden representation in this end-to-end model.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="1807.07281")

Code

Syntology Ran 1 of 13 code samples harvested from 3 repositories linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: community (archive-listed): 13 samples from 3 repositories, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

dhgrs/chainer-ClariNet mentioned on GitHub report
kensun0/Parallel-Wavenet mentioned on GitHubtf report
ksw0306/ClariNet mentioned on GitHubpytorchMIT report
rickyHong/ClariNet-WaveNet-repl mentioned on GitHubpytorchMIT report
tiberiu44/TTS-Cube mentioned on GitHubpytorchApache-2.0 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

13 samples harvested; 1 ran; 1 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
12unverified

Licence: 0 of the 13 samples are 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. “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.

log_sum_exp tiberiu44/TTS-Cube/cube/networks/loss.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · a42f23f7210ea856 · report
KL_gaussians ksw0306/ClariNet/loss.py community (archive-listed) unverified MIT (permissive) · 99b2eded38ce1abf · report
KL_gaussians rickyHong/ClariNet-WaveNet-repl/loss.py community (archive-listed) unverified MIT (permissive) · 57c9f8e5bb12cb77 · report
collate_fn ksw0306/ClariNet/data.py community (archive-listed) unverified MIT (permissive) · 4846dec26aaad0fb · report
collate_fn rickyHong/ClariNet-WaveNet-repl/data.py community (archive-listed) unverified MIT (permissive) · e2b09320a943125b · report
collate_fn_synthesize ksw0306/ClariNet/data.py community (archive-listed) unverified MIT (permissive) · ec4b02e7e489d13f · report
gaussian_loss ksw0306/ClariNet/loss.py community (archive-listed) unverified MIT (permissive) · a877c4698b24f4e6 · report
gaussian_loss rickyHong/ClariNet-WaveNet-repl/loss.py community (archive-listed) unverified MIT (permissive) · 09bc09927c87507a · report
load_checkpoint ksw0306/ClariNet/synthesize_student.py community (archive-listed) unverified MIT (permissive) · 0b918065d1f5caaf · report
load_checkpoint rickyHong/ClariNet-WaveNet-repl/synthesize_student.py community (archive-listed) unverified MIT (permissive) · 500d31e7c971c941 · report
sample_from_gaussian ksw0306/ClariNet/loss.py community (archive-listed) unverified MIT (permissive) · 43151884ea330907 · report
sample_from_gaussian rickyHong/ClariNet-WaveNet-repl/loss.py community (archive-listed) unverified MIT (permissive) · 8c58c097caa4d2e6 · report
stft ksw0306/ClariNet/modules.py community (archive-listed) unverified MIT (permissive) · f3e80a7e162563ee · report

Tasks

Speech SynthesisText to Speechtext-to-speech

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Bridge-net, ClariNet

AdamAttentionBridge-netClariNetConvolutionDV3 Attention BlockDV3 Convolution BlockDense ConnectionsDilated Causal ConvolutionDropoutGated Linear UnitL1 RegularizationMixture of Logistic DistributionsNormalizing FlowsReLUResidual ConnectionSoftmaxSoftsign ActivationWaveNetWeight Normalization

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