"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding

TL;DR

This paper investigates the application of Kolmogorov-Arnold Networks (KANs) to Spoken Language Understanding, demonstrating their effectiveness as replacements for linear layers in neural models and analyzing their attention mechanisms.

Contribution

It is the first to explore KANs in SLU tasks, integrating them into CNN and transformer models, and providing insights into their attention behavior on raw waveforms.

Findings

KAN layers can replace linear layers with comparable or better performance

KAN-enhanced models perform well across multiple SLU datasets

Insights into how KAN and linear layers attend to input regions

Abstract

Kolmogorov-Arnold Networks (KANs) have recently emerged as a promising alternative to traditional neural architectures, yet their application to speech processing remains under explored. This work presents the first investigation of KANs for Spoken Language Understanding (SLU) tasks. We experiment with 2D-CNN models on two datasets, integrating KAN layers in five different configurations within the dense block. The best-performing setup, which places a KAN layer between two linear layers, is directly applied to transformer-based models and evaluated on five SLU datasets with increasing complexity. Our results show that KAN layers can effectively replace the linear layers, achieving comparable or superior performance in most cases. Finally, we provide insights into how KAN and linear layers on top of transformers differently attend to input regions of the raw waveforms.