Effective Integration of KAN for Keyword Spotting
Audio and Speech Processing
2025-06-13 v3 Sound
Abstract
Keyword spotting (KWS) is an important speech processing component for smart devices with voice assistance capability. In this paper, we investigate if Kolmogorov-Arnold Networks (KAN) can be used to enhance the performance of KWS. We explore various approaches to integrate KAN for a model architecture based on 1D Convolutional Neural Networks (CNN). We find that KAN is effective at modeling high-level features in lower-dimensional spaces, resulting in improved KWS performance when integrated appropriately. The findings shed light on understanding KAN for speech processing tasks and on other modalities for future researchers.
Keywords
Cite
@article{arxiv.2409.08605,
title = {Effective Integration of KAN for Keyword Spotting},
author = {Anfeng Xu and Biqiao Zhang and Shuyu Kong and Yiteng Huang and Zhaojun Yang and Sangeeta Srivastava and Ming Sun},
journal= {arXiv preprint arXiv:2409.08605},
year = {2025}
}
Comments
Accepted to ICASSP 2025