mlsanityData to 7 Oct 2026

Speech and audio SSMs

113 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: speech, audio, mamba, speech enhancement, performance

Key facts. Speech and audio SSMs: 113 papers on arXiv since 2022 (data through 7 Oct 2026). 25 of its 113 mapped papers (22%) cite “Mamba in Speech: Towards an Alternative to Self-Attention” (2024, arXiv 2405.12609). 23 of its 113 mapped papers (20%) cite “An Investigation of Incorporating Mamba for Speech Enhancement” (2024, arXiv 2405.06573). 4 new papers 18 Sep–7 Oct.

What’s new

18 Sep – 7 Oct 2026

  1. Earlier · 4
  2. BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge
  3. MambaVoice: Lightweight Audiovisual Singing Voice Separation Via A Hybrid Mamba-Transformer Model
  4. SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schr"odinger Bridges
  5. HAMMER: Harmonic-Aware Parallel Context Modeling and Discriminator-Free Perceptual Optimization for Speech Enhancement

Foundations

Most cited by papers here

  1. Mamba in Speech: Towards an Alternative to Self-Attention2024cited by 25 here
  2. An Investigation of Incorporating Mamba for Speech Enhancement2024cited by 23 here
  3. Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation2024cited by 21 here
  4. SPMamba: State-space model is all you need in speech separation2024cited by 18 here
  5. Audio Mamba: Bidirectional State Space Model for Audio Representation Learning2024cited by 13 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 47 here
  2. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 5 here
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 73 here
  4. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 10 here
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 32 here
  6. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 21 here
  7. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 23 here
  8. 2024Mamba in Speech: Towards an Alternative to Self-Attentioncited by 25 here
  9. 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesiscited by 12 here
  10. 2024Rethinking Mamba in Speech Processing by Self-Supervised Modelscited by 5 here
14 more it builds on, not in this chain
  1. 2022Simplified State Space Layers for Sequence Modelingcited by 10 here
  2. 2022Structured State Space Decoder for Speech Recognition and Synthesiscited by 4 here
  3. 2023A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Modelscited by 7 here
  4. 2024VL-Mamba: Exploring State Space Models for Multimodal Learningcited by 4 here
  5. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 12 here
  6. 2024SPMamba: State-space model is all you need in speech separationcited by 18 here
  7. 2024TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platformscited by 5 here
  8. 2024SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Modelcited by 11 here
  9. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 18 here
  10. 2024Audio Mamba: Selective State Spaces for Self-Supervised Audio Representationscited by 10 here
  11. 2024Audio Mamba: Bidirectional State Space Model for Audio Representation Learningcited by 13 here
  12. 2024RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detectioncited by 8 here
  13. 2024Exploring the Capability of Mamba in Speech Applicationscited by 10 here
  14. 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Modelscited by 6 here

The 24 most cited of 139.

Browse

30 of 113, ranked 6–35

  1. 6Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis202412
  2. 7SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model202411
  3. 8Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations202410
  4. 9Exploring the Capability of Mamba in Speech Applications202410
  5. 10RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection20248
  6. 11A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models20237
  7. 12Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models20246
  8. 13TRAMBA: A Hybrid Transformer and Mamba Architecture for Practical Audio and Bone Conduction Speech Super Resolution and Enhancement on Mobile and Wearable Platforms20245
  9. 14Rethinking Mamba in Speech Processing by Self-Supervised Models20245
  10. 15Universal Speech Enhancement with Regression and Generative Mamba20254
All 30
  1. 16Mamba-SEUNet: Mamba UNet for Monaural Speech Enhancement20244
  2. 17Structured State Space Decoder for Speech Recognition and Synthesis20224
  3. 18TF-Mamba: A Time-Frequency Network for Sound Source Localization20243
  4. 19Mamba for Streaming ASR Combined with Unimodal Aggregation20243
  5. 20SepMamba: State-space models for speaker separation using Mamba20243
  6. 21XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection20243
  7. 22Spiking Structured State Space Model for Monaural Speech Enhancement20233
  8. 23xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement20252
  9. 24AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation20252
  10. 25An Exploration of Mamba for Speech Self-Supervised Models20252
  11. 26Audio Mamba: Pretrained Audio State Space Model For Audio Tagging20242
  12. 27SELD-Mamba: Selective State-Space Model for Sound Event Localization and Detection with Source Distance Estimation20242
  13. 28DeFT-Mamba: Universal Multichannel Sound Separation and Polyphonic Audio Classification20242
  14. 29DepMamba: Progressive Fusion Mamba for Multimodal Depression Detection20242
  15. 30SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model20242
  16. 31U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation20242
  17. 32Augmenting conformers with structured state-space sequence models for online speech recognition20232
  18. 33Samba-ASR: State-Of-The-Art Speech Recognition Leveraging Structured State-Space Models20251
  19. 34BiCrossMamba-ST: Speech Deepfake Detection with Bidirectional Mamba Spectro-Temporal Cross-Attention20251
  20. 35EDNet: A Versatile Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training20251