Papers › Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net

Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net

1 Jun 2020Interspeech 2020 6arXiv:2006.00687archive 2025-07-28

In this work, we tackle a denoising and dereverberation problem with a single-stage framework. Although denoising and dereverberation may be considered two separate challenging tasks, and thus, two modules are typically required for each task, we show that a single deep network can be shared to solve the two problems. To this end, we propose a new masking method called phase-aware beta-sigmoid mask (PHM), which reuses the estimated magnitude values to estimate the clean phase by respecting the triangle inequality in the complex domain between three signal components such as mixture, source and the rest. Two PHMs are used to deal with direct and reverberant source, which allows controlling the proportion of reverberation in the enhanced speech at inference time. In addition, to improve the speech enhancement performance, we propose a new time-domain loss function and show a reasonable performance gain compared to MSE loss in the complex domain. Finally, to achieve a real-time inference, an optimization strategy for U-Net is proposed which significantly reduces the computational overhead up to 88.9% compared to the na\"ive version.

PaperPDFConference PDFCode

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.

Code

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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingSpeech DenoisingSpeech Enhancement

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Dereverberation WHAMR! Non-Real-Time MultiScale+ PESQ 3.16 #3 of 3 Archive leaderboard report
Speech Dereverberation WHAMR! Non-Real-Time MultiScale+ SI-SDR 10.4 #3 of 3 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge Non-Real-Time MultiScale+ PESQ-NB 3.01 #33 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge Non-Real-Time MultiScale+ SI-SDR-WB 16.22 #33 of 36 Archive leaderboard report
Speech Enhancement WHAMR! Non-Real-Time MultiScale+ PESQ 1.52 #4 of 4 Archive leaderboard report
Speech Enhancement WHAMR! Non-Real-Time MultiScale+ SI-SDR 5.33 #4 of 4 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