Papers › Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

8 Jun 2018arXiv:1806.03185archive 2025-07-28

Daniel Stoller, Sebastian Ewert, Simon Dixon

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end. Therefore, we investigate end-to-end source separation in the time-domain, which allows modelling phase information and avoids fixed spectral transformations. Due to high sampling rates for audio, employing a long temporal input context on the sample level is difficult, but required for high quality separation results because of long-range temporal correlations. In this context, we propose the Wave-U-Net, an adaptation of the U-Net to the one-dimensional time domain, which repeatedly resamples feature maps to compute and combine features at different time scales. We introduce further architectural improvements, including an output layer that enforces source additivity, an upsampling technique and a context-aware prediction framework to reduce output artifacts. Experiments for singing voice separation indicate that our architecture yields a performance comparable to a state-of-the-art spectrogram-based U-Net architecture, given the same data. Finally, we reveal a problem with outliers in the currently used SDR evaluation metrics and suggest reporting rank-based statistics to alleviate this problem.

PaperPDFCodeCode 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="1806.03185")

Code

Syntology Ran 1 of 19 code samples harvested from 5 repositories linked to this paper; 18 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 9 samples from 1 repository, 0 ran; community (archive-listed): 10 samples from 4 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.

f90/Wave-U-Net officialmentioned in papermentioned on GitHubtfMIT report
MattSegal/speech-enhancement mentioned on GitHubpytorch report
ShichengChen/WaveNetSeparateAudio mentioned on GitHubpytorch report
ShichengChen/WaveUNet mentioned on GitHubpytorch report
f90/Wave-U-Net-Pytorch mentioned on GitHubpytorchMIT report
jperezlapillo/Hyper-Wave-U-Net mentioned on GitHubtfMIT report
lucas-dunker/stem-separator-amt 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

19 samples harvested; 1 ran; 0 honoured the contract we drafted; 18 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 · fixture could not drive it
18unverified

Licence: 1 of the 19 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 5 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.

compute_mean_metrics f90/Wave-U-Net/Evaluate.py official repository unverified MIT (permissive) · 7ef7210907a0d9be · report
crop_and_concat f90/Wave-U-Net/Utils.py official repository unverified MIT (permissive) · f3054ff75a9faf20 · report
getNumParams f90/Wave-U-Net/Utils.py official repository unverified MIT (permissive) · 404b97b66e233e0d · report
getTrainableVariables f90/Wave-U-Net/Utils.py official repository unverified MIT (permissive) · e119d722ad3969f8 · report
independent_outputs f90/Wave-U-Net/Models/OutputLayer.py official repository unverified MIT (permissive) · 7fd1fa630f0e11bd · report
learned_interpolation_layer f90/Wave-U-Net/Models/InterpolationLayer.py official repository unverified MIT (permissive) · 0af32c8aa2b13465 · report
take_all_snippets f90/Wave-U-Net/Datasets.py official repository unverified MIT (permissive) · 773e07dfbc4df2db · report
take_random_snippets f90/Wave-U-Net/Datasets.py official repository unverified MIT (permissive) · 6950f34674f12037 · report
take_snippets_at_pos f90/Wave-U-Net/Datasets.py official repository unverified MIT (permissive) · b8955c9d5cd1a2ed · report
subsample_chunk_random MattSegal/speech-enhancement/src/datasets/speech/noisy_librispeech/librispeech_dataset.py community (archive-listed) ran · fixture could not drive it fingerprinted no licence file found · pointer only · 19db27f0a2d1b55c · report
build_sinc_filter f90/Wave-U-Net-Pytorch/model/resample.py community (archive-listed) unverified MIT (permissive) · 78f6f864d89c2756 · report
centre_crop f90/Wave-U-Net-Pytorch/model/crop.py community (archive-listed) unverified MIT (permissive) · 2803fec1aab36834 · report
compute_loss f90/Wave-U-Net-Pytorch/model/utils.py community (archive-listed) unverified MIT (permissive) · 950864364ec0b8d2 · report
get_lr f90/Wave-U-Net-Pytorch/utils.py community (archive-listed) unverified MIT (permissive) · b293995d32808cdd · report
get_padding satvik-venkatesh/Wave-U-net-TF2/wave_u_net.py community (archive-listed) unverified MIT (permissive) · d8372ce707c3095c · report
initialize_config haoxiangsnr/Wave-U-Net-for-Speech-Enhancement/util/utils.py community (archive-listed) unverified MIT (permissive) · aafe9da12cdcd105 · report
load_checkpoint haoxiangsnr/Wave-U-Net-for-Speech-Enhancement/util/utils.py community (archive-listed) unverified MIT (permissive) · 8fdba4f9ae28cbe8 · report
load_model f90/Wave-U-Net-Pytorch/model/utils.py community (archive-listed) unverified MIT (permissive) · abf55a235181f2e0 · report
wave_u_net satvik-venkatesh/Wave-U-net-TF2/wave_u_net.py community (archive-listed) unverified MIT (permissive) · 8efc19a229bb0bc7 · report

Tasks

Audio Source SeparationMusic Source Separation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Music Source Separation MUSDB18 STL2 SDR (avg) 3.23 #27 of 27 Archive leaderboard report
Music Source Separation MUSDB18 STL2 SDR (bass) 3.21 #27 of 27 Archive leaderboard report
Music Source Separation MUSDB18 STL2 SDR (drums) 4.22 #27 of 27 Archive leaderboard report
Music Source Separation MUSDB18 STL2 SDR (other) 2.25 #27 of 27 Archive leaderboard report
Music Source Separation MUSDB18 STL2 SDR (vocals) 3.25 #27 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Concatenated Skip ConnectionConvolutionMax PoolingReLUU-Net

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