mlsanityData to 7 Oct 2026

A Two-Stage Band-Split Mamba-2 Network For Music Separation

arXiv 2409.06245 ↗First posted 10 Sep 2024cs.SD eess.AScited by 2

On the map: State-space sequence models (S4, Mamba) → Speech and audio SSMs

Abstract (arXiv)

Music source separation (MSS) aims to separate mixed music into its distinct tracks, such as vocals, bass, drums, and more. MSS is considered to be a challenging audio separation task due to the complexity of music signals. Although the RNN and Transformer architecture are not perfect, they are commonly used to model the music sequence for MSS. Recently, Mamba-2 has already demonstrated high efficiency in various sequential modeling tasks, but its superiority has not been investigated in MSS. This paper applies Mamba-2 with a two-stage strategy, which introduces residual mapping based on the mask method, effectively compensating for the details absent in the mask and further improving separation performance. Experiments confirm the superiority of bidirectional Mamba-2 and the effectiveness of the two-stage network in MSS. The source code is publicly accessible at https://github.com/baijinglin/TS-BSmamba2.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 26 of its 42 references that are in the map. First posted on arXiv 10 Sep 2024.

Builds on

26 of 42 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  5. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,424
  6. 2018Group Normalizationcited by 1,514
  7. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  8. 2016Language Modeling with Gated Convolutional Networkscited by 688
  9. 2022Hybrid Transformers for Music Source Separationcited by 134
  10. 2018Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separationcited by 125
  11. 2019Music Source Separation in the Waveform Domaincited by 98
  12. 2021Hybrid Spectrogram and Waveform Source Separationcited by 90
14 more
  1. 2022Music Source Separation with Band-split RNNcited by 69
  2. 2021Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separationcited by 48
  3. 2021Music Demixing Challenge 2021cited by 38
  4. 2023Music Source Separation with Band-Split RoPE Transformercited by 36
  5. 2019End-to-end Microphone Permutation and Number Invariant Multi-channel Speech Separationcited by 31
  6. 2021KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixingcited by 24
  7. 2018MMDenseLSTM: An efficient combination of convolutional and recurrent neural networks for audio source separationcited by 19
  8. 2020Meta-learning Extractors for Music Source Separationcited by 18
  9. 2023Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)cited by 11
  10. 2024SCNet: Sparse Compression Network for Music Source Separationcited by 10
  11. 2022Taylor, Can You Hear Me Now? A Taylor-Unfolding Framework for Monaural Speech Enhancementcited by 7
  12. 2023Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3cited by 4
  13. 2024Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNetcited by 3
  14. 2022TaylorBeamformer: Learning All-Neural Beamformer for Multi-Channel Speech Enhancement from Taylor's Approximation Theorycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Mamba-Based Model for Automatic Chord Recognitioncited by 0
  2. 2026Iterative Audio Separation with Mixture Consistency via MIMO Model Extensioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions
  2. 2024DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification
  3. 2026Input-Adaptive Spectral Feature Compression by Sequence Modeling for Source Separation ↗
  4. 2025User-guided Generative Source Separation
  5. 2026MambaVoice: Lightweight Audiovisual Singing Voice Separation Via A Hybrid Mamba-Transformer Model
  6. 2024U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation
  7. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
  8. 2026Omni-directional attention mechanism based on Mamba for speech separation