Papers › FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech...

FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement

29 Oct 2020arXiv:2010.15508archive 2025-07-28

Xiang Hao, Xiangdong Su, Radu Horaud, Xiaofei Li

This paper proposes a full-band and sub-band fusion model, named as FullSubNet, for single-channel real-time speech enhancement. Full-band and sub-band refer to the models that input full-band and sub-band noisy spectral feature, output full-band and sub-band speech target, respectively. The sub-band model processes each frequency independently. Its input consists of one frequency and several context frequencies. The output is the prediction of the clean speech target for the corresponding frequency. These two types of models have distinct characteristics. The full-band model can capture the global spectral context and the long-distance cross-band dependencies. However, it lacks the ability to modeling signal stationarity and attending the local spectral pattern. The sub-band model is just the opposite. In our proposed FullSubNet, we connect a pure full-band model and a pure sub-band model sequentially and use practical joint training to integrate these two types of models' advantages. We conducted experiments on the DNS challenge (INTERSPEECH 2020) dataset to evaluate the proposed method. Experimental results show that full-band and sub-band information are complementary, and the FullSubNet can effectively integrate them. Besides, the performance of the FullSubNet also exceeds that of the top-ranked methods in the DNS Challenge (INTERSPEECH 2020).

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 21 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 21 samples from 3 repositories, 17 ran (17 with no instrument failure; 0 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

audio-westlakeu/fullsubnet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fast FullSubNet: Accelerate Full-band and Sub-band Fusion Model for Single-channel... (arXiv:2212.09019; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
marialaraa/adresso_analysis mentioned on GitHubSyntology: not harvested report
seorim0/DNN-based-Speech-Enhancement-in-the-frequency-domain mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
tommy19970714/FullSubNetWithASR mentioned on GitHubpytorchMITSyntology: 11 samples, 9 ran (0 instrument-failed) · 2 unverified report
yunyangzeng/taploss mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
sc0ttms/SE-FullSubNet paddlenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: 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

21 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 4 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.

1ran · honoured contract
16ran
4unverified

Licence: 0 of the 21 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; 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.

seorim0/DNN-based-Speech-Enhancement-in-the-frequency-domain community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
calculate_total_params train_interface.py ran · honoured contract MIT (permissive) · 43af741407c3119e · report fixture: signature our_model:callable/0/? · returned int · level recorded 2026-09-22
tommy19970714/FullSubNetWithASR community (archive-listed) 11 samples, 9 ran (0 instrument-failed) · 2 unverified
SI_SDR audio_zen/metrics.py ran MIT (permissive) · d0515795fdc671d5 · report fixture: signature reference:ndarray/3/float, estimation:ndarray/3/float, sr:int/0/int · returned ndarray · level recorded 2026-09-24
compress_cIRM audio_zen/acoustics/mask.py ran fingerprinted MIT (permissive) · 0306c94b0fb722ad · report fixture: signature mask:Tensor/2/float, K:int/0/int, C:float/0/float · returned Tensor · level recorded 2026-09-24
cumulative_norm audio_zen/model/module/feature_norm.py ran fingerprinted MIT (permissive) · f262d023c4c06497 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24
decompress_cIRM audio_zen/acoustics/mask.py ran fingerprinted MIT (permissive) · 921fe9eca3d2f597 · report fixture: signature mask:Tensor/2/float, K:int/0/int, limit:float/0/float · returned Tensor · level recorded 2026-09-24
initialize_module audio_zen/utils.py ran MIT (permissive) · cb42367b074aa9be · report fixture: signature path:str/0/str, args:dict/0/?, initialize:bool/0/bool · returned SimpleModel · level recorded 2026-09-24
load_checkpoint in 277 papers audio_zen/utils.py ran MIT (permissive) · bdaef26cae8309bd · report fixture: signature checkpoint_path:str/0/str, device:str/0/str · returned Tensor · level recorded 2026-09-24
mc_stft audio_zen/acoustics/feature.py ran MIT (permissive) · f84ec968085a47e5 · report fixture: signature y_s:Tensor/3/float, n_fft:int/0/int, hop_length:int/0/int, win_length:int/0/int · returned Tensor · level recorded 2026-09-24
stft in 21 papers audio_zen/acoustics/feature.py ran MIT (permissive) · 3eb077cda4d7d5b9 · report fixture: signature y:Tensor/2/float, n_fft:int/0/int, hop_length:int/0/int, win_length:int/0/int · returned Tensor · level recorded 2026-09-24
transform_pesq_range audio_zen/acoustics/utils.py ran fingerprinted MIT (permissive) · 698f3380463d1400 · report fixture: signature pesq_score:float/0/float · returned float · level recorded 2026-09-24
istft in 7 papers audio_zen/acoustics/feature.py unverified MIT (permissive) · e0e1eed9bac3d920 · report
print_tensor_info audio_zen/utils.py unverified MIT (permissive) · 3099b5d08820498b · report
yunyangzeng/taploss community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
apply_filterbank FullSubNet/audio_zen/acoustics/filtebank.py ran MIT (permissive) · 73a5db3a96cba5c8 · report fixture: signature specgram:Tensor/3/float, filterbank:Tensor/2/float · returned Tensor · level recorded 2026-09-25
compress_cIRM FullSubNet/audio_zen/acoustics/mask.py ran fingerprinted MIT (permissive) · 702b9611643e4127 · report fixture: signature mask:Tensor/2/float, K:int/0/int, C:float/0/float · returned Tensor · level recorded 2026-09-24
decompress_cIRM FullSubNet/audio_zen/acoustics/mask.py ran fingerprinted MIT (permissive) · f09f5094643e68f4 · report fixture: signature mask:Tensor/2/float, K:int/0/int, limit:float/0/float · returned Tensor · level recorded 2026-09-24
initialize_module FullSubNet/audio_zen/utils.py ran MIT (permissive) · 8c1ce2ab24fa69e0 · report fixture: signature path:str/0/str, args:dict/0/?, initialize:bool/0/bool · returned FullSubNetModel · level recorded 2026-09-24
inverse_filterbank FullSubNet/audio_zen/acoustics/filtebank.py ran fingerprinted MIT (permissive) · 2be9f5174fb8a644 · report fixture: signature filtered_specgram:Tensor/3/float, filterbank:Tensor/2/float · returned Tensor · level recorded 2026-09-25
mag_phase FullSubNet/audio_zen/acoustics/feature.py ran MIT (permissive) · 2e7ab324da47c617 · report fixture: signature complex_tensor:Tensor/2/complex · returned tuple · level recorded 2026-09-25
stft in 21 papers FullSubNet/audio_zen/acoustics/feature.py ran MIT (permissive) · 9f9fa01352b9ea06 · report fixture: signature y:Tensor/3/float, n_fft:int/0/int, hop_length:int/0/int, win_length:int/0/int · returned tuple · level recorded 2026-09-24
istft in 7 papers FullSubNet/audio_zen/acoustics/feature.py unverified MIT (permissive) · ee6f4a73f6e1070d · report
stft in 21 papers Demucs/denoiser/denoiser/stft_loss.py unverified MIT (permissive) · d40b7ea72ed329ed · report

Tasks

Speech Enhancement

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Enhancement Deep Noise Suppression (DNS) Challenge FullSubNet PESQ-NB 3.305 #22 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge FullSubNet PESQ-WB 2.777 #22 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge FullSubNet SI-SDR-WB 17.29 #22 of 36 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.

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