"KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908380290875392 |
|---|---|
| author | Koudounas, Alkis La Quatra, Moreno Pastor, Eliana Siniscalchi, Sabato Marco Baralis, Elena |
| author_facet | Koudounas, Alkis La Quatra, Moreno Pastor, Eliana Siniscalchi, Sabato Marco Baralis, Elena |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_20176 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | "KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding Koudounas, Alkis La Quatra, Moreno Pastor, Eliana Siniscalchi, Sabato Marco Baralis, Elena Computation and Language Machine Learning Audio and Speech Processing 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. |
| title | "KAN you hear me?" Exploring Kolmogorov-Arnold Networks for Spoken Language Understanding |
| topic | Computation and Language Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.20176 |