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 repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2302.14748")

Code

Syntology Ran 10 of 11 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 10 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sp-uhh/sgmse-bbed officialmentioned on GitHubpytorchMIT report
sp-uhh/sgmse mentioned on GitHubpytorchMIT 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

11 samples harvested; 10 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

10ran
1unverified

Licence: 0 of the 11 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 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. “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.

energy_ratios sp-uhh/sgmse-bbed/sgmse/util/other.py official repository ran MIT (permissive) · e4185b3ed3a097b6 · report
get_act sp-uhh/sgmse-bbed/sgmse/backbones/ncsnpp_utils/layers.py official repository ran MIT (permissive) · 216c782f9d07ef3a · report
get_activation sp-uhh/sgmse-bbed/sgmse/backbones/dcunet.py official repository ran MIT (permissive) · eb5ba43dadcbda84 · report
get_window sp-uhh/sgmse-bbed/sgmse/data_module.py official repository ran MIT (permissive) · 9e802d63089d5d62 · report
make_unet_encoder_decoder_args sp-uhh/sgmse-bbed/sgmse/backbones/dcunet.py official repository ran MIT (permissive) · 9ce3b9f139bb58ff · report
mean_conf_int sp-uhh/sgmse-bbed/sgmse/util/other.py official repository ran MIT (permissive) · f36a0fc077e7eeca · report
si_sdr_components sp-uhh/sgmse-bbed/sgmse/util/other.py official repository ran fingerprinted MIT (permissive) · 5f57b9e7cfd0a20d · report
torch_complex_from_reim sp-uhh/sgmse-bbed/sgmse/backbones/shared.py official repository ran MIT (permissive) · 63cec12b7bc5275c · report
unet_decoder_args sp-uhh/sgmse-bbed/sgmse/backbones/dcunet.py official repository ran MIT (permissive) · 0eabe078d2ed0794 · report
variance_scaling sp-uhh/sgmse-bbed/sgmse/backbones/ncsnpp_utils/layers.py official repository ran MIT (permissive) · 3ac11bfe0ae80195 · report
ncsn_conv1x1 sp-uhh/sgmse-bbed/sgmse/backbones/ncsnpp_utils/layers.py official repository unverified MIT (permissive) · 85b2235eb7afaa4f · report

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