Papers › Efficient Neural Audio Synthesis

Efficient Neural Audio Synthesis

23 Feb 2018ICML 2018 7arXiv:1802.08435archive 2025-07-28

Nal Kalchbrenner, Erich Elsen, Karen Simonyan, Seb Noury, Norman Casagrande, Edward Lockhart, Florian Stimberg, Aaron van den Oord, Sander Dieleman, Koray Kavukcuoglu

Sequential models achieve state-of-the-art results in audio, visual and textual domains with respect to both estimating the data distribution and generating high-quality samples. Efficient sampling for this class of models has however remained an elusive problem. With a focus on text-to-speech synthesis, we describe a set of general techniques for reducing sampling time while maintaining high output quality. We first describe a single-layer recurrent neural network, the WaveRNN, with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model. The compact form of the network makes it possible to generate 24kHz 16-bit audio 4x faster than real time on a GPU. Second, we apply a weight pruning technique to reduce the number of weights in the WaveRNN. We find that, for a constant number of parameters, large sparse networks perform better than small dense networks and this relationship holds for sparsity levels beyond 96%. The small number of weights in a Sparse WaveRNN makes it possible to sample high-fidelity audio on a mobile CPU in real time. Finally, we propose a new generation scheme based on subscaling that folds a long sequence into a batch of shorter sequences and allows one to generate multiple samples at once. The Subscale WaveRNN produces 16 samples per step without loss of quality and offers an orthogonal method for increasing sampling efficiency.

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="1802.08435")

Code

Syntology Ran 3 of 3 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong.

By repository: community (archive-listed): 2 samples from 2 repositories, 2 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.

16 repositories listed; official and paper-mentioned ones first.

CorentinJ/Real-Time-Voice-Cloning mentioned on GitHubtfNOASSERTION report
GPUPhobia/vocal-mask mentioned on GitHubpytorch report
OlaWod/my-wavernn mentioned on GitHubpytorch report
Rongjiehuang/Multiband-WaveRNN mentioned on GitHubpytorch report
anandaswarup/waveRNN mentioned on GitHubpytorchMIT report
caizexin/tf_multispeakerTTS_fc mentioned on GitHubtfMIT report
ciaua/score_lyrics_free_svg mentioned on GitHubpytorch report
dipjyoti92/SC-WaveRNN mentioned on GitHubpytorch report
dipjyoti92/TTS-Style-Transfer mentioned on GitHubpytorchMIT report
fatchord/WaveRNN mentioned on GitHubpytorch report
google/lyra mentioned on GitHubApache-2.0 report
mkotha/WaveRNN mentioned on GitHubpytorch report
tiberiu44/TTS-Cube mentioned on GitHubpytorchApache-2.0 report
tigthor/Voice-Cloning-AI mentioned on GitHubpytorchNOASSERTION report
coqui-ai/TTS pytorchMPL-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

3 samples harvested; 3 ran; 2 honoured the contract we drafted; 0 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.

2ran · honoured contract
1ran · our draft was wrong

Licence: 1 of the 3 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 2 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.

cosine_decay Rongjiehuang/Multiband-WaveRNN/train_wavernn.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · f0b0dd80e32ae81d · report
filter_none mkotha/WaveRNN/layers/overtone.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · e7889f3a0209e24c · report
np_now identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 2af6a131384db5c8 · report

Tasks

Audio SynthesisSpeech 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

Introduced by this paper: WaveRNN

PruningReLUSigmoid ActivationSoftmaxTanh ActivationWaveRNN

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