Keyword Mamba: Spoken Keyword Spotting with State Space Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Hanyu, Dong, Wenlong, Mao, Qirong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913982972952576
author Ding, Hanyu
Dong, Wenlong
Mao, Qirong
author_facet Ding, Hanyu
Dong, Wenlong
Mao, Qirong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07363
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Keyword Mamba: Spoken Keyword Spotting with State Space Models
Ding, Hanyu
Dong, Wenlong
Mao, Qirong
Sound
Audio and Speech Processing
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.
title Keyword Mamba: Spoken Keyword Spotting with State Space Models
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.07363