Papers › SEGAN: Speech Enhancement Generative Adversarial Network

SEGAN: Speech Enhancement Generative Adversarial Network

28 Mar 2017arXiv:1703.09452archive 2025-07-28

Santiago Pascual, Antonio Bonafonte, Joan Serrà

Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues, deep networks are being increasingly used, thanks to their ability to learn complex functions from large example sets. In this work, we propose the use of generative adversarial networks for speech enhancement. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them. We evaluate the proposed model using an independent, unseen test set with two speakers and 20 alternative noise conditions. The enhanced samples confirm the viability of the proposed model, and both objective and subjective evaluations confirm the effectiveness of it. With that, we open the exploration of generative architectures for speech enhancement, which may progressively incorporate further speech-centric design choices to improve their performance.

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 39 code samples harvested from 10 repositories linked to this paper: 26 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 31 samples from 9 repositories, 22 ran (19 with no instrument failure; 3 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

santi-pdp/segan officialmentioned in papermentioned on GitHubtfMITSyntology: 8 samples, 4 ran (0 instrument-failed) · 4 unverified report
RaphaelOlivier/gard_eval2_public mentioned on GitHubpytorchSyntology: not harvested report
YosukeSugiura/SEGAN mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
andreser09/segan mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
anicolson/DeepXi mentioned on GitHubtfMPL-2.0Syntology: not harvested report
asadullah797/segan_impr mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
deNsuh/segan-pytorch mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
develooper1994/MasterThesis mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified 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
haozh7109/SEGAN-TensorFlow2 mentioned on GitHubtfApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
hatsunexym/YAMAHA-Corp mentioned on GitHubtfSyntology: not harvested report
huylenguyen806/vnasr mentioned on GitHubtfApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
pquochuy/idsegan mentioned on GitHubtfSyntology: not harvested report
pquochuy/sasegan mentioned on GitHubtfSyntology: not harvested report
rickyHong/segan-pytorch-repl mentioned on GitHubpytorchSyntology: not harvested report
santi-pdp/segan_pytorch mentioned on GitHubpytorchMITSyntology: 14 samples, 13 ran (2 instrument-failed) · 1 unverified report
shifaspv/SE-FFTNet-tensorflow-implemenatation mentioned on GitHubtfSyntology: not harvested report
ssarfjoo/improvedsegan mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
sufengniu/segan_multi mentioned on GitHubtfMITSyntology: 1 sample, 0 ran · 1 unverified report
usimarit/TiramisuASR mentioned on GitHubtfApache-2.0Syntology: not harvested report
usimarit/vnasr mentioned on GitHubtfApache-2.0Syntology: not harvested 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

39 samples harvested: 26 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 13 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.

2ran · our draft was wrong
1ran; the contract check could not run
23ran
13unverified

Licence: 6 of the 39 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 10 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. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

santi-pdp/segan official repository 8 samples, 4 ran (0 instrument-failed) · 4 unverified
de_emph data_loader.py ran fingerprinted MIT (permissive) · f97b465794902557 · report fixture: signature y:ndarray/1/float, coeff:float/0/float · returned ndarray · level recorded 2026-09-25
read_and_slice make_tfrecords.py ran MIT (permissive) · ab225f7af41a0ef3 · report fixture: signature filename:str/0/str, wav_canvas_size:int/0/int, stride:float/0/float · returned ndarray · level recorded 2026-09-25
scalar_summary ops.py ran MIT (permissive) · 35f13999f3f8f9dd · report fixture: signature name:str/0/str, x:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-25
slice_signal make_tfrecords.py ran MIT (permissive) · 46c1eb78df53cf66 · report fixture: signature signal:ndarray/1/int, window_size:int/0/int, stride:float/0/float · returned ndarray · level recorded 2026-09-25
gaussian_noise_layer ops.py unverified MIT (permissive) · 7f91d893c058c60b · report
pre_emph data_loader.py unverified MIT (permissive) · f00acf17aed0af5a · report
read_and_decode in 5 papers data_loader.py unverified MIT (permissive) · 28105186fd5104d4 · report
sample_random_walk ops.py unverified MIT (permissive) · b6fb2cc68fa10225 · report
YosukeSugiura/SEGAN community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
wav_write data.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 1b028fcf0c1ec0d5 · report fixture: signature filename:str/0/str, x:ndarray/1/float, fs:int/0/int · returned int · level recorded 2026-09-22
andreser09/segan community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
pre_emph data_loader.py ran MIT (permissive) · 4c2a62db536d3e11 · report fixture: signature x:EagerTensor/1/float, coeff:float/0/float · returned EagerTensor · level recorded 2026-09-26
scalar_summary ops.py ran MIT (permissive) · 610ca41dfb04b88a · report fixture: signature name:str/0/str, x:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-26
read_and_decode in 5 papers data_loader.py unverified MIT (permissive) · 534a5aaa629f0b62 · report
asadullah797/segan_impr community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
read_and_slice make_tfrecords.py ran MIT (permissive) · 9fd6da88395e5dfe · report fixture: signature filename:str/0/str, wav_canvas_size:int/0/int, stride:float/0/float · returned ndarray · level recorded 2026-09-26
slice_signal make_tfrecords.py ran MIT (permissive) · dbce5ca80cee35d6 · report fixture: signature signal:ndarray/1/float, window_size:int/0/int, stride:float/0/float · returned ndarray · level recorded 2026-09-26
read_and_decode in 5 papers data_loader.py unverified MIT (permissive) · 455f04cbcd882c4d · report
develooper1994/MasterThesis community (archive-listed) 3 samples, 0 ran · 3 unverified
check_input_sampling clean.py unverified no licence file found · pointer only · d9f2796539b63330 · report
downsample in 59 papers clean.py unverified no licence file found · pointer only · fba9aaf89912df38 · report
get_input_sampling clean.py unverified no licence file found · pointer only · 41f93d7418a0950c · report
haozh7109/SEGAN-TensorFlow2 community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
emphasis Utility/Py_data_Preprocess_Hao.py ran Apache-2.0 (permissive) · 1056ff58d881d749 · report fixture: signature signal_batch:ndarray/3/float, emph_coeff:float/0/float, pre:bool/0/bool · returned ndarray · level recorded 2026-09-26
emphasis_librosa Utility/Py_data_Preprocess_Hao.py ran Apache-2.0 (permissive) · cae4d9938745ed11 · report fixture: signature signal_batch:ndarray/3/float, emph_coeff:float/0/float, pre:bool/0/bool · returned ndarray · level recorded 2026-09-26
load_config in 389 papers SEGAN_TrainMaster.py ran Apache-2.0 (permissive) · 8058adbabbf8b825 · report fixture: signature config_file:str/0/str · returned dict · level recorded 2026-09-26
load_datasets in 50 papers Inference_singleShot.py ran Apache-2.0 (permissive) · 69a97611e4cfefac · report fixture: signature opt:OptConfig/0/? · returned tuple · level recorded 2026-09-26
huylenguyen806/vnasr community (archive-listed) 1 sample, 0 ran · 1 unverified
deserialize in 10 papers tensorflow_asr/callbacks.py unverified Apache-2.0 (permissive) · efd738a0bc3cc757 · report
santi-pdp/segan_pytorch community (archive-listed) 14 samples, 13 ran (2 instrument-failed) · 1 unverified
KLD in 6 papers segan/models/ops.py ran fingerprinted MIT (permissive) · c8cdd110f18d46c9 · report fixture: signature mean_p:Tensor/2/float, std_p:Tensor/2/float, mean_g:Tensor/2/float, std_g:Tensor/2/float · returned Tensor · level recorded 2026-09-26
build_norm_layer in 14 papers segan/models/modules.py ran MIT (permissive) · b9130696e49c3339 · report fixture: signature norm_type:str/0/str, param:callable/0/?, num_feats:int/0/int · returned BatchNorm1d · level recorded 2026-09-26
collate_fn in 500 papers segan/datasets/se_dataset.py ran MIT (permissive) · 82ea88d96fdaa51d · report fixture: signature batch:list/1/tuple · returned list · level recorded 2026-09-26
denormalize_wave_minmax segan/utils.py ran fingerprinted MIT (permissive) · d81dd81a9f083f86 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-26
flip in 32 papers
census: 3 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 3, kind float, dtype float32
segan/models/modules.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · b380f42b5b71cc47 · report fixture: signature x:Tensor/3/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
get_grads in 13 papers segan/models/ops.py ran MIT (permissive) · 26c162c3caa1223a · report fixture: signature model:callable/0/? · returned Tensor · level recorded 2026-09-26
l2normalize in 31 papers segan/models/spectral_norm.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · bedff51745d2cf84 · report fixture: signature v:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
make_divN segan/utils.py ran MIT (permissive) · cf249ef7bc710ec2 · report fixture: signature tensor:Tensor/3/float, N:int/0/int, method:str/0/str · returned Tensor · level recorded 2026-09-26
pos_code segan/models/core.py ran MIT (permissive) · 2638e76ea8d2f15e · report fixture: signature chunk_pos:Tensor/1/int, x:Tensor/3/float · returned Tensor · level recorded 2026-09-26
sinc in 9 papers segan/models/modules.py ran MIT (permissive) · 7c9569388b69a763 · report fixture: signature band:float/0/float, t_right:Tensor/1/float, cuda:bool/0/bool · returned Tensor · level recorded 2026-09-26
slice_signal segan/datasets/se_dataset.py ran MIT (permissive) · d8d685caed96ccb2 · report fixture: signature signal:ndarray/1/float, window_sizes:list/1/int, stride:float/0/float · returned list · level recorded 2026-09-26
uttname2spkid segan/utils.py ran fingerprinted MIT (permissive) · 9c7d42585a206ba4 · report fixture: signature uttname:str/0/str · returned str · level recorded 2026-09-26
varlen_wav_collate segan/datasets/vc_dataset.py ran MIT (permissive) · 3d5991b1620d158d · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-26
make_optimizer in 32 papers segan/models/ops.py unverified MIT (permissive) · 42bb0a5113fe251c · report
ssarfjoo/improvedsegan community (archive-listed) 1 sample, 0 ran · 1 unverified
read_and_decode in 5 papers data_loader.py unverified MIT (permissive) · 67b26950d2b2b2b8 · report
sufengniu/segan_multi community (archive-listed) 1 sample, 0 ran · 1 unverified
read_and_decode in 5 papers data_loader.py unverified MIT (permissive) · c4f1ac5600121aba · report

Tasks

Speech Enhancement

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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