{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/high-fidelity-speech-enhancement-with-band","title":"High Fidelity Speech Enhancement with Band-split RNN","arxiv_id":"2212.00406","date":"2022-12-01","proceeding":null,"authors":["Jianwei Yu","Yi Luo","Hangting Chen","Rongzhi Gu","Chao Weng"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2212.00406v2","url_pdf":"https://arxiv.org/pdf/2212.00406v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"high-fidelity-speech-enhancement-with-band","repo_url":"https://github.com/sungwon23/bsrnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset":"Deep Noise Suppression (DNS) Challenge","model":"BSRNN-S + MRSD","rank_in_archive_order":7,"of":36,"metrics":{"PESQ-NB":"3.89","PESQ-WB":"3.53","SI-SDR-WB":"21.4","STOI":"98.4"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset":"Deep Noise Suppression (DNS) Challenge","model":"BSRNN-16k","rank_in_archive_order":8,"of":36,"metrics":{"PESQ-NB":"3.87","PESQ-WB":"3.45","SI-SDR-WB":"21.1","STOI":"98.3"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset":"Deep Noise Suppression (DNS) Challenge","model":"BSRNN-S","rank_in_archive_order":10,"of":36,"metrics":{"PESQ-WB":"3.42","SI-SDR-WB":"21.3"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset":"Deep Noise Suppression (DNS) Challenge","model":"BSRNN","rank_in_archive_order":11,"of":36,"metrics":{"PESQ-NB":"3.79","PESQ-WB":"3.32","STOI":"98"},"uses_additional_data":false},{"leaderboard":"/sota/speech-enhancement-on-deep-noise-suppression","task":"Speech Enhancement","dataset":"Deep Noise Suppression (DNS) Challenge","model":"BSRNN-S + MGD","rank_in_archive_order":31,"of":36,"metrics":{"PESQ-NB":"3.85","SI-SDR-WB":"21.4","STOI":"98.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.00406","atlas_url":"https://app.syntology.ai/?focus=2212.00406","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}