mlsanityData to 14 Oct 2026

An Investigation of Incorporating Mamba for Speech Enhancement

arXiv 2405.06573 ↗First posted 10 May 2024cs.SD cs.AI eess.AScited by 62

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

Abstract (arXiv)

This work aims to investigate the use of a recently proposed, attention-free, scalable state-space model (SSM), Mamba, for the speech enhancement (SE) task. In particular, we employ Mamba to deploy different regression-based SE models (SEMamba) with different configurations, namely basic, advanced, causal, and non-causal. Furthermore, loss functions either based on signal-level distances or metric-oriented are considered. Experimental evidence shows that SEMamba attains a competitive PESQ of 3.55 on the VoiceBank-DEMAND dataset with the advanced, non-causal configuration. A new state-of-the-art PESQ of 3.69 is also reported when SEMamba is combined with Perceptual Contrast Stretching (PCS). Compared against Transformed-based equivalent SE solutions, a noticeable FLOPs reduction up to ~12% is observed with the advanced non-causal configurations. Finally, SEMamba can be used as a pre-processing step before automatic speech recognition (ASR), showing competitive performance against recent SE solutions.

Key facts. Cited by 62 papers in the map (data through 14 Oct 2026). Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 26 of its 46 references that are in the map. First posted on arXiv 10 May 2024.

Builds on

26 of 46 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation27 Mar
  2. 2023Spiking Structured State Space Model for Monaural Speech Enhancement7 Sep
  3. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models1 Jun

Other references · 23

  1. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  4. 2022Hungry Hungry Hippos: Towards Language Modeling with State Space Modelscited by 499
  5. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
  6. 2018SDR - half-baked or well done?cited by 423
  7. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 216
  8. 2020Real Time Speech Enhancement in the Waveform Domaincited by 186
  9. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  10. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  11. 2023MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectracited by 52
  12. 2020On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regressioncited by 33
11 more
  1. 2021DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancementcited by 33
  2. 2020Speech Enhancement using Self-Adaptation and Multi-Head Self-Attentioncited by 28
  3. 2017End-to-End Waveform Utterance Enhancement for Direct Evaluation Metrics Optimization by Fully Convolutional Neural Networkscited by 26
  4. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancementcited by 23
  5. 2017Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verificationcited by 19
  6. 2023Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancementcited by 13
  7. 2022SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Taskscited by 8
  8. 2022Perceptual Contrast Stretching on Target Feature for Speech Enhancementcited by 6
  9. 2024Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performancecited by 6
  10. 2023Attention-based Speech Enhancement Using Human Quality Perception Modellingcited by 2
  11. 2023D4AM: A General Denoising Framework for Downstream Acoustic Modelscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 16; 2025: 31; 2026: 15.

62 papers.

Sort:

By area:

  1. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 60
  2. 2024A Survey of Mambacited by 39
  3. 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesiscited by 23
  4. 2024Rethinking Mamba in Speech Processing by Self-Supervised Modelscited by 11
  5. 2024Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancementcited by 10
  6. 2025Universal Speech Enhancement with Regression and Generative Mambacited by 7
  7. 2024SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Modelcited by 6
  8. 2025Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latencycited by 6
  9. 2025Fake-Mamba: Real-Time Speech Deepfake Detection Using Bidirectional Mamba as Self-Attention's Alternativecited by 6
  10. 2024TF-Mamba: A Time-Frequency Network for Sound Source Localizationcited by 5
  11. 2024MECG-E: Mamba-based ECG Enhancer for Baseline Wander Removalcited by 5
  12. 2024Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognitioncited by 5
38 more
  1. 2025xLSTM-SENet: xLSTM for Single-Channel Speech Enhancementcited by 4
  2. 2025Schr"odinger Bridge Consistency Trajectory Models for Speech Enhancementcited by 4
  3. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  4. 2025EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Trainingcited by 3
  5. 2025Schr"odinger Bridge Mamba for One-Step Speech Enhancementcited by 3
  6. 2024CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruningcited by 2
  7. 2024MSEMG: Surface Electromyography Denoising with a Mamba-based Efficient Networkcited by 2
  8. 2024MSECG: Incorporating Mamba for Robust and Efficient ECG Super-Resolutioncited by 2
  9. 2025Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractionscited by 2
  10. 2025Deep Active Speech Cancellation with Mamba-Masking Networkcited by 2
  11. 2025Technologies on Effectiveness and Efficiency: A Survey of State Spaces Modelscited by 2
  12. 2025An Exploration of Mamba for Speech Self-Supervised Modelscited by 2
  13. 2025MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancementcited by 2
  14. 2025Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidancecited by 2
  15. 2025ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancementcited by 2
  16. 2025Diffusion Buffer for Online Generative Speech Enhancementcited by 2
  17. 2026Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarioscited by 2
  18. 2024Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mambacited by 1
  19. 2024Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancementcited by 1
  20. 2025TF-MLPNet: Tiny Real-Time Neural Speech Separationcited by 1
  21. 2025MLMA: Towards Multilingual ASR With Mamba-based Architecturescited by 1
  22. 2025Regularized Schr"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancementcited by 1
  23. 2025MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequencecited by 1
  24. 2026Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakerscited by 1
  25. 2026Quaternion Self-Attention with Shared Scorescited by 1
  26. 2024aTENNuate: Optimized Real-time Speech Enhancement with Deep SSMs on Raw Audiocited by 0
  27. 2024Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancementcited by 0
  28. 2025Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberationcited by 0
  29. 2025Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speechcited by 0
  30. 2025Keyword Mamba: Spoken Keyword Spotting with State Space Modelscited by 0
  31. 2025Leveraging Mamba with Full-Face Vision for Audio-Visual Speech Enhancementcited by 0
  32. 2025Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regionscited by 0
  33. 2025Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognitioncited by 0
  34. 2025An overview of neural architectures for self-supervised audio representation learning from masked spectrogramscited by 0
  35. 2025Exploring Resolution-Wise Shared Attention in Hybrid Mamba-U-Nets for Improved Cross-Corpus Speech Enhancementcited by 0
  36. 2025Robust Photoplethysmography Signal Denoising via Mamba Networkscited by 0
  37. 2025Condition-Invariant fMRI Decoding of Speech Intelligibility with Deep State Space Modelcited by 0
  38. 2025ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extractioncited by 0

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MC-SEMamba: A Simple Multi-channel Extension of SEMamba
  2. 2024Selective State Space Model for Monaural Speech Enhancement
  3. 2025Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model
  4. 2024Exploring the Capability of Mamba in Speech Applications
  5. 2026HAMMER: Harmonic-Aware Parallel Context Modeling and Discriminator-Free Perceptual Optimization for Speech Enhancement
  6. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models
  7. 2025Mixture-of-Mamba: Enhancing Multi-Modal State-Space Models with Modality-Aware Sparsity
  8. 2025Long-Context Modeling Networks for Monaural Speech Enhancement: A Comparative Study