# Speech and audio SSMs

Area: [State-space sequence models (S4, Mamba)](https://mlsanity.com/ssm/index.md). HTML: https://mlsanity.com/ssm/speech-and-audio-ssms/

## Key facts

- Speech and audio SSMs: 113 papers on arXiv since 2022 (data through 14 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).
- 5 new papers 18 Sep–14 Oct.

## Most cited here

- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024), cited by 25 papers here
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024), cited by 23 papers here
- [Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation](https://mlsanity.com/paper/2403.18257/) (2024), cited by 21 papers here
- [SPMamba: State-space model is all you need in speech separation](https://mlsanity.com/paper/2404.02063/) (2024), cited by 18 papers here
- [Audio Mamba: Bidirectional State Space Model for Audio Representation Learning](https://mlsanity.com/paper/2406.03344/) (2024), cited by 13 papers here
- [Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis](https://mlsanity.com/paper/2407.09732/) (2024), cited by 12 papers here
- [SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model](https://mlsanity.com/paper/2405.11831/) (2024), cited by 11 papers here
- [Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations](https://mlsanity.com/paper/2406.02178/) (2024), cited by 10 papers here
- [Exploring the Capability of Mamba in Speech Applications](https://mlsanity.com/paper/2406.16808/) (2024), cited by 10 papers here
- [RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection](https://mlsanity.com/paper/2406.06086/) (2024), cited by 8 papers here

## New (18 Sep–14 Oct)

- [BridgeCodec: Mamba Enhanced Neural Audio Codec with Schr"odinger Bridge at Low Bitrate](https://mlsanity.com/paper/2610.15453/) (2026-10-11)
- [BiMamba2 Masked Discrete-Unit Prediction for Multilingual Speech Representation for Unsupervised Speech in the Wild Challenge](https://mlsanity.com/paper/2609.28758/) (2026-09-23)
- [MambaVoice: Lightweight Audiovisual Singing Voice Separation Via A Hybrid Mamba-Transformer Model](https://mlsanity.com/paper/2609.26635/) (2026-09-22)
- [SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schr"odinger Bridges](https://mlsanity.com/paper/2609.26000/) (2026-09-22)
- [HAMMER: Harmonic-Aware Parallel Context Modeling and Discriminator-Free Perceptual Optimization for Speech Enhancement](https://mlsanity.com/paper/2609.21171/) (2026-09-18)