# Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions

arXiv: https://arxiv.org/abs/2508.14556 · HTML: https://mlsanity.com/paper/2508.14556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 25 references that are in the map.
- First posted on arXiv 20 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [HiPPO: Recurrent Memory with Optimal Polynomial Projections](https://mlsanity.com/paper/2008.07669/) (2020)
- [On the Parameterization and Initialization of Diagonal State Space Models](https://mlsanity.com/paper/2206.11893/) (2022)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024)
- [Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation](https://mlsanity.com/paper/2109.05418/) (2021)
- [Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation](https://mlsanity.com/paper/2403.18257/) (2024)
- [Music Demixing Challenge 2021](https://mlsanity.com/paper/2108.13559/) (2021)
- [Music Source Separation with Band-Split RoPE Transformer](https://mlsanity.com/paper/2309.02612/) (2023)
- [DeepSinger: Singing Voice Synthesis with Data Mined From the Web](https://mlsanity.com/paper/2007.04590/) (2020)
- [The Sound Demixing Challenge 2023 unicodex2013 Music Demixing Track](https://mlsanity.com/paper/2308.06979/) (2023)
- [Multi-scale Multi-band DenseNets for Audio Source Separation](https://mlsanity.com/paper/1706.09588/) (2017)
- [LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation](https://mlsanity.com/paper/2010.11631/) (2020)
- [Not All Attention Is Needed: Gated Attention Network for Sequence Data](https://mlsanity.com/paper/1912.00349/) (2019)
- [SCNet: Sparse Compression Network for Music Source Separation](https://mlsanity.com/paper/2401.13276/) (2024)
- [Robust Singing Voice Transcription Serves Synthesis](https://mlsanity.com/paper/2405.09940/) (2024)
- [Score and Lyrics-Free Singing Voice Generation](https://mlsanity.com/paper/1912.11747/) (2019)

## Abstract (arXiv)

We introduce a new music source separation model tailored for accurate vocal isolation. Unlike Transformer-based approaches, which often fail to capture intermittently occurring vocals, our model leverages Mamba2, a recent state space model, to better capture long-range temporal dependencies. To handle long input sequences efficiently, we combine a band-splitting strategy with a dual-path architecture. Experiments show that our approach outperforms recent state-of-the-art models, achieving a cSDR of 11.03 dB-the best reported to date-and delivering substantial gains in uSDR. Moreover, the model exhibits stable and consistent performance across varying input lengths and vocal occurrence patterns. These results demonstrate the effectiveness of Mamba-based models for high-resolution audio processing and open up new directions for broader applications in audio research.