Papers › Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based...

Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement

28 Feb 2023arXiv:2302.14748archive 2025-07-28

Bunlong Lay, Simon Welker, Julius Richter, Timo Gerkmann

Recently, score-based generative models have been successfully employed for the task of speech enhancement. A stochastic differential equation is used to model the iterative forward process, where at each step environmental noise and white Gaussian noise are added to the clean speech signal. While in limit the mean of the forward process ends at the noisy mixture, in practice it stops earlier and thus only at an approximation of the noisy mixture. This results in a discrepancy between the terminating distribution of the forward process and the prior used for solving the reverse process at inference. In this paper, we address this discrepancy and propose a forward process based on a Brownian bridge. We show that such a process leads to a reduction of the mismatch compared to previous diffusion processes. More importantly, we show that our approach improves in objective metrics over the baseline process with only half of the iteration steps and having one hyperparameter less to tune.

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 11 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 11 ran (7 with no instrument failure; 4 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sp-uhh/sgmse-bbed officialmentioned on GitHubpytorchMITSyntology: 11 samples, 11 ran (4 instrument-failed) · 0 unverified report
sp-uhh/sgmse mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and... (arXiv:2406.06185; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4ran · our draft was wrong
6ran

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 sp-uhh/sgmse-bbed. “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.

sp-uhh/sgmse-bbed official repository 11 samples, 11 ran (4 instrument-failed) · 0 unverified
energy_ratios sgmse/util/other.py ran MIT (permissive) · e4185b3ed3a097b6 · report fixture: signature s_hat:ndarray/1/float, s:ndarray/1/float, n:ndarray/1/float · returned tuple · level recorded 2026-09-25
get_act in 56 papers sgmse/backbones/ncsnpp_utils/layers.py ran · our draft was wrong MIT (permissive) · 216c782f9d07ef3a · report fixture: signature config:str/0/str · returned ReLU · level recorded 2026-09-24
get_activation in 218 papers sgmse/backbones/dcunet.py ran · our draft was wrong MIT (permissive) · eb5ba43dadcbda84 · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-24
get_window in 7 papers sgmse/data_module.py ran · honoured contract MIT (permissive) · 9e802d63089d5d62 · report fixture: signature window_type:str/0/str, window_length:int/0/int · returned Tensor · level recorded 2026-09-24
make_unet_encoder_decoder_args sgmse/backbones/dcunet.py ran MIT (permissive) · 9ce3b9f139bb58ff · report fixture: signature encoder_args:list/1/tuple, decoder_args:str/0/str · returned tuple · level recorded 2026-09-24
mean_conf_int sgmse/util/other.py ran fingerprinted MIT (permissive) · f36a0fc077e7eeca · report fixture: signature data:list/1/float, confidence:float/0/float · returned tuple · level recorded 2026-09-25
ncsn_conv1x1 in 21 papers sgmse/backbones/ncsnpp_utils/layers.py ran MIT (permissive) here; the stored copy is pointer only · 85b2235eb7afaa4f · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, bias:bool/0/bool, dilation:int/0/int, init_scale:float/0/float, padding:int/0/int · returned Conv2d · level recorded 2026-09-26
si_sdr_components sgmse/util/other.py ran fingerprinted MIT (permissive) · 5f57b9e7cfd0a20d · report fixture: signature s_hat:ndarray/1/float, s:ndarray/1/float, n:ndarray/1/float · returned tuple · level recorded 2026-09-25
torch_complex_from_reim in 6 papers sgmse/backbones/shared.py ran MIT (permissive) · 63cec12b7bc5275c · report fixture: signature re:Tensor/2/float, im:Tensor/2/float · returned Tensor · level recorded 2026-09-24
unet_decoder_args sgmse/backbones/dcunet.py ran · our draft was wrong MIT (permissive) · 0eabe078d2ed0794 · report fixture: signature encoders:tuple/1/tuple, skip_connections:bool/0/bool · returned tuple · level recorded 2026-09-24
variance_scaling in 31 papers sgmse/backbones/ncsnpp_utils/layers.py ran · our draft was wrong MIT (permissive) · 3ac11bfe0ae80195 · report fixture: signature scale:float/0/float, mode:str/0/str, distribution:str/0/str, in_axis:int/0/int, out_axis:int/0/int, dtype:dtype/0/?, device:str/0/str · returned function · level recorded 2026-09-24

Tasks

Speech Enhancement

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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