mlsanityData to 14 Oct 2026

ReZero: Region-customizable Sound Extraction

arXiv 2308.16892 ↗First posted 31 Aug 2023eess.AS cs.AI cs.SDcited by 10

Not on the map. Why?

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/.

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

30 of 61 references.

References · 30

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  2. 2018Neural Ordinary Differential Equationscited by 3,779
  3. 2016HyperNetworkscited by 1,027
  4. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  5. 2018SDR - half-baked or well done?cited by 423
  6. 2016Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separationcited by 191
  7. 2020Attention is All You Need in Speech Separationcited by 185
  8. 2018VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Maskingcited by 73
  9. 2022Music Source Separation with Band-split RNNcited by 70
  10. 2022TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separationcited by 63
  11. 2019Demucs: Deep Extractor for Music Sources with extra unlabeled data remixedcited by 54
  12. 2018gpuRIR: A Python Library for Room Impulse Response Simulation with GPU Accelerationcited by 46
18 more
  1. 2019End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separationcited by 31
  2. 2020What's All the FUSS About Free Universal Sound Separation Data?cited by 22
  3. 2020The Cone of Silence: Speech Separation by Localizationcited by 21
  4. 2021Personalized Speech Enhancement: New Models and Comprehensive Evaluationcited by 21
  5. 2022High Fidelity Speech Enhancement with Band-split RNNcited by 16
  6. 2022Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancementcited by 14
  7. 2022Distance-Based Sound Separationcited by 8
  8. 2023TEA-PSE 3.0: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System For ICASSP 2023 DNS Challengecited by 8
  9. 2021Nonlinear Spatial Filtering in Multichannel Speech Enhancementcited by 6
  10. 2022Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domaincited by 6
  11. 2022Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separationcited by 5
  12. 2021Multi-channel Narrow-band Deep Speech Separation with Full-band Permutation Invariant Trainingcited by 4
  13. 2022Learning to Separate Voices by Spatial Regionscited by 4
  14. 2023Multi-Microphone Speaker Separation by Spatial Regionscited by 4
  15. 2023Focus on the Sound around You: Monaural Target Speaker Extraction via Distance and Speaker Informationcited by 3
  16. 2022Deep Neural Mel-Subband Beamformer for In-car Speech Separationcited by 2
  17. 2023Fast Random Approximation of Multi-channel Room Impulse Responsecited by 2
  18. 2020Two Channel Audio Zooming System For Smartphonecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 3.

10 papers.

  1. 2025Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarioscited by 4
  2. 2024DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classificationcited by 3
  3. 2024Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Cluescited by 2
  4. 2025SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extractioncited by 2
  5. 2025Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidancecited by 2
  6. 2026Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarioscited by 2
  7. 2026Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakerscited by 1
  8. 2026Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)cited by 1
  9. 2025SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenescited by 0
  10. 2025LSZone: A Lightweight Spatial Information Modeling Architecture for Real-time In-car Multi-zone Speech Separationcited by 0