Keyword Mamba: Spoken Keyword Spotting with State Space Models
On the map: State-space sequence models (S4, Mamba) → Speech and audio SSMs
Abstract (arXiv)
Keyword spotting (KWS) is an essential task in speech processing. It is widely used in voice assistants and smart devices. Deep learning models like CNNs, RNNs, and Transformers have performed well in KWS. However, they often struggle to handle long-term patterns and stay efficient at the same time. In this work, we present Keyword Mamba, a new architecture for KWS. It uses a neural state space model (SSM) called Mamba. We apply Mamba along the time axis and also explore how it can replace the self-attention part in Transformer models. We test our model on the Google Speech Commands datasets. The results show that Keyword Mamba reaches strong accuracy with fewer parameters and lower computational cost. To our knowledge, this is the first time a state space model has been used for KWS. These results suggest that Mamba has strong potential in speech-related tasks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 46 of its 56 references that are in the map. First posted on arXiv 10 Aug 2025.
Builds on
46 of 56 references.
Closest ancestors · 10
Same direction, newest first
- 2024U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation24 Dec
- 2024XLSR-Mamba: A Dual-Column Bidirectional State Space Model for Spoofing Attack Detection15 Nov
- 2024Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition11 Nov
- 2024Speech-Mamba: Long-Context Speech Recognition with Selective State Spaces Models27 Sep
- 2024Rethinking Mamba in Speech Processing by Self-Supervised Models11 Sep
- 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis13 Jul
- 2024Audio Mamba: Bidirectional State Space Model for Audio Representation Learning5 Jun
- 2024Mamba in Speech: Towards an Alternative to Self-Attention21 May
- 2024An Investigation of Incorporating Mamba for Speech Enhancement10 May
- 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation27 Mar
Other references · 36
- 2017Attention Is All You Needcited by 60,361
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
- 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
- 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
- 2024VMamba: Visual State Space Modelcited by 969
- 2022In-context Learning and Induction Headscited by 964
- 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
- 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
- 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 605
- 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 424
24 more
- 2021Pay Attention to MLPscited by 368
- 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 169
- 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
- 2017Hello Edge: Keyword Spotting on Microcontrollerscited by 110
- 2024Demystify Mamba in Vision: A Linear Attention Perspectivecited by 102
- 2024Mamba-ND: Selective State Space Modeling for Multi-Dimensional Datacited by 84
- 2023Simple Hardware-Efficient Long Convolutions for Sequence Modelingcited by 62
- 2024Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Modelcited by 62
- 2021Keyword Transformer: A Self-Attention Model for Keyword Spottingcited by 60
- 2019Temporal Convolution for Real-time Keyword Spotting on Mobile Devicescited by 49
- 2021Broadcasted Residual Learning for Efficient Keyword Spottingcited by 48
- 2020Streaming keyword spotting on mobile devicescited by 47
- 2021Deep Spoken Keyword Spotting: An Overviewcited by 43
- 2020MatchboxNet: 1D Time-Channel Separable Convolutional Neural Network Architecture for Speech Commands Recognitioncited by 36
- 2024Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakerscited by 28
- 2024Exploring Token Pruning in Vision State Space Modelscited by 28
- 2019Small-Footprint Keyword Spotting on Raw Audio Data with Sinc-Convolutionscited by 20
- 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Modelcited by 18
- 2022ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spottingcited by 11
- 2020AutoKWS: Keyword Spotting with Differentiable Architecture Searchcited by 10
- 2024Dark Experience for Incremental Keyword Spottingcited by 4
- 2025AnalyticKWS: Towards Exemplar-Free Analytic Class Incremental Learning for Small-footprint Keyword Spottingcited by 4
- 2021Text Anchor Based Metric Learning for Small-footprint Keyword Spottingcited by 3
- 2024UCIL: An Unsupervised Class Incremental Learning Approach for Sound Event Detectioncited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Exploring the Capability of Mamba in Speech Applications
- 2026Omni-directional attention mechanism based on Mamba for speech separation
- 2024A Survey of Mamba
- 2024Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks
- 2024BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection
- 2024Selective State Space Model for Monaural Speech Enhancement
- 2025An Exploration of Mamba for Speech Self-Supervised Models
- 2024An Empirical Study of Mamba-based Language Models