# High Fidelity Speech Enhancement with Band-split RNN

arXiv: https://arxiv.org/abs/2212.00406 · HTML: https://mlsanity.com/paper/2212.00406/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2022.

## Built on by (most cited first, 16 of 16)

- [Kimi-Audio Technical Report](https://mlsanity.com/paper/2504.18425/) (2025)
- [MoonCast: High-Quality Zero-Shot Podcast Generation](https://mlsanity.com/paper/2503.14345/) (2025)
- [ReZero: Region-customizable Sound Extraction](https://mlsanity.com/paper/2308.16892/) (2023)
- [Source Separation by Flow Matching](https://mlsanity.com/paper/2505.16119/) (2025)
- [GASS: Generalizing Audio Source Separation with Large-scale Data](https://mlsanity.com/paper/2310.00140/) (2023)
- [Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement](https://mlsanity.com/paper/2408.12425/) (2024)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning](https://mlsanity.com/paper/2312.06118/) (2023)
- [Music Enhancement with Deep Filters: A Technical Report for The ICASSP 2024 Cadenza Challenge](https://mlsanity.com/paper/2404.11116/) (2024)
- [Training-Free Multi-Step Audio Source Separation](https://mlsanity.com/paper/2505.19534/) (2025)
- [DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration](https://mlsanity.com/paper/2505.23515/) (2025)
- [PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction](https://mlsanity.com/paper/2607.08111/) (2026)
- [The NUS-HLT System for ICASSP2024 ICMC-ASR Grand Challenge](https://mlsanity.com/paper/2312.16002/) (2023)
- [The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN](https://mlsanity.com/paper/2603.09187/) (2026)
- [BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention](https://mlsanity.com/paper/2606.12662/) (2026)
- [Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends](https://mlsanity.com/paper/2608.30326/) (2026)

## Abstract (arXiv)

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.