# ReZero: Region-customizable Sound Extraction

arXiv: https://arxiv.org/abs/2308.16892 · HTML: https://mlsanity.com/paper/2308.16892/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 31 Aug 2023.

## Builds on (most cited first, 30 of 30)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking](https://mlsanity.com/paper/1810.04826/) (2018)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [Demucs: Deep Extractor for Music Sources with extra unlabeled data remixed](https://mlsanity.com/paper/1909.01174/) (2019)
- [gpuRIR: A Python Library for Room Impulse Response Simulation with GPU Acceleration](https://mlsanity.com/paper/1810.11359/) (2018)
- [End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separation](https://mlsanity.com/paper/1910.14104/) (2019)
- [What's All the FUSS About Free Universal Sound Separation Data?](https://mlsanity.com/paper/2011.00803/) (2020)
- [The Cone of Silence: Speech Separation by Localization](https://mlsanity.com/paper/2010.06007/) (2020)
- [Personalized Speech Enhancement: New Models and Comprehensive Evaluation](https://mlsanity.com/paper/2110.09625/) (2021)
- [High Fidelity Speech Enhancement with Band-split RNN](https://mlsanity.com/paper/2212.00406/) (2022)
- [Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement](https://mlsanity.com/paper/2206.13310/) (2022)
- [Distance-Based Sound Separation](https://mlsanity.com/paper/2207.00562/) (2022)
- [TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challenge](https://mlsanity.com/paper/2303.07704/) (2023)
- [Nonlinear Spatial Filtering in Multichannel Speech Enhancement](https://mlsanity.com/paper/2104.11033/) (2021)
- [Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain](https://mlsanity.com/paper/2206.15423/) (2022)
- [Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation](https://mlsanity.com/paper/2212.08348/) (2022)
- [Multi-channel Narrow-band Deep Speech Separation with Full-band Permutation Invariant Training](https://mlsanity.com/paper/2110.05966/) (2021)
- [Learning to Separate Voices by Spatial Regions](https://mlsanity.com/paper/2207.04203/) (2022)
- [Multi-Microphone Speaker Separation by Spatial Regions](https://mlsanity.com/paper/2303.07143/) (2023)
- [Focus on the Sound around You: Monaural Target Speaker Extraction via Distance and Speaker Information](https://mlsanity.com/paper/2306.16241/) (2023)
- [Deep Neural Mel-Subband Beamformer for In-car Speech Separation](https://mlsanity.com/paper/2211.12590/) (2022)
- [Fast Random Approximation of Multi-channel Room Impulse Response](https://mlsanity.com/paper/2304.08052/) (2023)
- [Two Channel Audio Zooming System For Smartphone](https://mlsanity.com/paper/2001.04940/) (2020)

## Built on by (most cited first, 10 of 10)

- [Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios](https://mlsanity.com/paper/2505.14517/) (2025)
- [DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification](https://mlsanity.com/paper/2409.12413/) (2024)
- [Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues](https://mlsanity.com/paper/2409.12415/) (2024)
- [SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction](https://mlsanity.com/paper/2506.00273/) (2025)
- [Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance](https://mlsanity.com/paper/2507.02791/) (2025)
- [Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios](https://mlsanity.com/paper/2601.12345/) (2026)
- [Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers](https://mlsanity.com/paper/2603.23723/) (2026)
- [Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)](https://mlsanity.com/paper/2604.07522/) (2026)
- [SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenes](https://mlsanity.com/paper/2509.18561/) (2025)
- [LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separation](https://mlsanity.com/paper/2510.10687/) (2025)

## Abstract (arXiv)

We introduce region-customizable sound extraction (ReZero), a general and flexible framework for the multi-channel region-wise sound extraction (R-SE) task. R-SE task aims at extracting all active target sounds (e.g., human speech) within a specific, user-defined spatial region, which is different from conventional and existing tasks where a blind separation or a fixed, predefined spatial region are typically assumed. The spatial region can be defined as an angular window, a sphere, a cone, or other geometric patterns. Being a solution to the R-SE task, the proposed ReZero framework includes (1) definitions of different types of spatial regions, (2) methods for region feature extraction and aggregation, and (3) a multi-channel extension of the band-split RNN (BSRNN) model specified for the R-SE task. We design experiments for different microphone array geometries, different types of spatial regions, and comprehensive ablation studies on different system configurations. Experimental results on both simulated and real-recorded data demonstrate the effectiveness of ReZero. Demos are available at https://innerselfm.github.io/rezero/.