Papers › High Fidelity Speech Enhancement with Band-split RNN

High Fidelity Speech Enhancement with Band-split RNN

1 Dec 2022arXiv:2212.00406archive 2025-07-28

Jianwei Yu, Yi Luo, Hangting Chen, Rongzhi Gu, Chao Weng

Despite the rapid progress in speech enhancement (SE) research, enhancing the quality of desired speech in environments with strong noise and interfering speakers remains challenging. In this paper, we extend the application of the recently proposed band-split RNN (BSRNN) model to full-band SE and personalized SE (PSE) tasks. To mitigate the effects of unstable high-frequency components in full-band speech, we perform bi-directional and uni-directional band-level modeling to low-frequency and high-frequency subbands, respectively. For PSE task, we incorporate a speaker enrollment module into BSRNN to utilize target speaker information. Moreover, we utilize a MetricGAN discriminator (MGD) and a multi-resolution spectrogram discriminator (MRSD) to improve perceptual quality metrics. Experimental results show that our system outperforms various top-ranking SE systems, achieves state-of-the-art (SOTA) results on the DNS-2020 test set and ranks among the top 3 in the DNS-2023 challenge.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

sungwon23/bsrnn mentioned on GitHubpytorch 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

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

Tasks

Speech EnhancementVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MRSD PESQ-NB 3.89 #7 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MRSD PESQ-WB 3.53 #7 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MRSD SI-SDR-WB 21.4 #7 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MRSD STOI 98.4 #7 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-16k PESQ-NB 3.87 #8 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-16k PESQ-WB 3.45 #8 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-16k SI-SDR-WB 21.1 #8 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-16k STOI 98.3 #8 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S PESQ-WB 3.42 #10 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S SI-SDR-WB 21.3 #10 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN PESQ-NB 3.79 #11 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN PESQ-WB 3.32 #11 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN STOI 98 #11 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MGD PESQ-NB 3.85 #31 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MGD SI-SDR-WB 21.4 #31 of 36 Archive leaderboard report
Speech Enhancement Deep Noise Suppression (DNS) Challenge BSRNN-S + MGD STOI 98.4 #31 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.

Methods

Test

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