Papers › MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement

8 Apr 2021arXiv:2104.03538archive 2025-07-28

Szu-Wei Fu, Cheng Yu, Tsun-An Hsieh, Peter Plantinga, Mirco Ravanelli, Xugang Lu, Yu Tsao

The discrepancy between the cost function used for training a speech enhancement model and human auditory perception usually makes the quality of enhanced speech unsatisfactory. Objective evaluation metrics which consider human perception can hence serve as a bridge to reduce the gap. Our previously proposed MetricGAN was designed to optimize objective metrics by connecting the metric with a discriminator. Because only the scores of the target evaluation functions are needed during training, the metrics can even be non-differentiable. In this study, we propose a MetricGAN+ in which three training techniques incorporating domain-knowledge of speech processing are proposed. With these techniques, experimental results on the VoiceBank-DEMAND dataset show that MetricGAN+ can increase PESQ score by 0.3 compared to the previous MetricGAN and achieve state-of-the-art results (PESQ score = 3.15).

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="2104.03538")

Code

Syntology Ran 0 of 11 code samples harvested from 1 repository linked to this paper; 11 have no recorded run.

By repository: community (archive-listed): 11 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

JasonSWFu/MetricGAN mentioned on GitHub report
wooseok-shin/MetricGAN-plus-pytorch mentioned on GitHubpytorchApache-2.0 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; 0 ran; 0 honoured the contract we drafted; 11 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.

11unverified

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 wooseok-shin/MetricGAN-plus-pytorch. “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.

CMOS_normalize wooseok-shin/MetricGAN-plus-pytorch/metric_functions/compute_metric.py community (archive-listed) unverified Apache-2.0 (permissive) · fb683a717c75e052 · report
PESQ_normalize wooseok-shin/MetricGAN-plus-pytorch/metric_functions/compute_metric.py community (archive-listed) unverified Apache-2.0 (permissive) · 87b6c8bd6b25280e · report
SSNR wooseok-shin/MetricGAN-plus-pytorch/metric_functions/metric_helper.py community (archive-listed) unverified Apache-2.0 (permissive) · 1077627ee114c941 · report
collate_fn_G wooseok-shin/MetricGAN-plus-pytorch/dataloader.py community (archive-listed) unverified Apache-2.0 (permissive) · 3e07e541b703b78b · report
get_spec_and_phase wooseok-shin/MetricGAN-plus-pytorch/signal_processing.py community (archive-listed) unverified Apache-2.0 (permissive) · 01ffe2e07304ae79 · report
lpcoeff wooseok-shin/MetricGAN-plus-pytorch/metric_functions/metric_helper.py community (archive-listed) unverified Apache-2.0 (permissive) · 67f3a00cfe3b0711 · report
pad_sequence wooseok-shin/MetricGAN-plus-pytorch/dataloader.py community (archive-listed) unverified Apache-2.0 (permissive) · a8dc14dce213a37b · report
spectral_magnitude wooseok-shin/MetricGAN-plus-pytorch/signal_processing.py community (archive-listed) unverified Apache-2.0 (permissive) · d08f0cbc110051dd · report
transform_spec_to_wav wooseok-shin/MetricGAN-plus-pytorch/signal_processing.py community (archive-listed) unverified Apache-2.0 (permissive) · c0f0679c079fa005 · report
trim_mos wooseok-shin/MetricGAN-plus-pytorch/metric_functions/metric_helper.py community (archive-listed) unverified Apache-2.0 (permissive) · 1f6cd6dc5f0af4e4 · report
xavier_init_layer wooseok-shin/MetricGAN-plus-pytorch/model.py community (archive-listed) unverified Apache-2.0 (permissive) · 77bf89e77ca97f11 · report

Tasks

Speech Enhancement

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Enhancement VoiceBank + DEMAND MetricGAN+ CBAK 3.16 #26 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND MetricGAN+ COVL 3.64 #26 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND MetricGAN+ CSIG 4.14 #26 of 42 Archive leaderboard report
Speech Enhancement VoiceBank + DEMAND MetricGAN+ PESQ (wb) 3.15 #26 of 42 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