Effective Integration of KAN for Keyword Spotting

TL;DR

This paper explores integrating Kolmogorov-Arnold Networks (KAN) with 1D CNNs to improve keyword spotting performance in speech processing, demonstrating KAN's effectiveness in modeling high-level features.

Contribution

It introduces a novel integration of KAN with CNNs for keyword spotting, highlighting its benefits in modeling high-level features in speech tasks.

Findings

KAN improves KWS accuracy when integrated with CNNs

High-level feature modeling is enhanced by KAN

The approach offers insights for future speech processing research

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.