# From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology

arXiv: https://arxiv.org/abs/2412.17778 · HTML: https://mlsanity.com/paper/2412.17778/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 39 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019)
- [KAN or MLP: A Fairer Comparison](https://mlsanity.com/paper/2407.16674/) (2024)
- [Pad'e Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks](https://mlsanity.com/paper/1907.06732/) (2019)
- [Learning Activation Functions to Improve Deep Neural Networks](https://mlsanity.com/paper/1412.6830/) (2014)
- [Mamba in Speech: Towards an Alternative to Self-Attention](https://mlsanity.com/paper/2405.12609/) (2024)
- [Kolmogorov-Arnold Transformer](https://mlsanity.com/paper/2409.10594/) (2024)
- [CMGAN: Conformer-based Metric GAN for Speech Enhancement](https://mlsanity.com/paper/2203.15149/) (2022)
- [SELM: Speech Enhancement Using Discrete Tokens and Language Models](https://mlsanity.com/paper/2312.09747/) (2023)
- [DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancement](https://mlsanity.com/paper/2104.13002/) (2021)
- [Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks](https://mlsanity.com/paper/2010.09458/) (2020)
- [Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement](https://mlsanity.com/paper/2308.08926/) (2023)
- [SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks](https://mlsanity.com/paper/2210.14474/) (2022)
- [SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model](https://mlsanity.com/paper/2411.07751/) (2024)
- [TridentSE: Guiding Speech Enhancement with 32 Global Tokens](https://mlsanity.com/paper/2210.12995/) (2022)
- [Selective State Space Model for Monaural Speech Enhancement](https://mlsanity.com/paper/2411.06217/) (2024)

## Built on by (most cited first, 2 of 2)

- [Aligning Generative Speech Enhancement with Perceptual Feedback](https://mlsanity.com/paper/2507.09929/) (2025)
- [Training-Free Intelligibility-Guided Observation Addition for Noisy ASR](https://mlsanity.com/paper/2602.20967/) (2026)

## Abstract (arXiv)

Deep neural network (DNN)-based speech enhancement (SE) usually uses conventional activation functions, which lack the expressiveness to capture complex multiscale structures needed for high-fidelity SE. Group-Rational KAN (GR-KAN), a variant of Kolmogorov-Arnold Networks (KAN), retains KAN's expressiveness while improving scalability on complex tasks. We adapt GR-KAN to existing DNN-based SE by replacing dense layers with GR-KAN layers in the time-frequency (T-F) domain MP-SENet and adapting GR-KAN's activations into the 1D CNN layers in the time-domain Demucs. Results on Voicebank-DEMAND show that GR-KAN requires up to 4x fewer parameters while improving PESQ by up to 0.1. In contrast, KAN, facing scalability issues, outperforms MLP on a small-scale signal modeling task but fails to improve MP-SENet. We demonstrate the first successful use of KAN-based methods for consistent improvement in both time- and SoTA TF-domain SE, establishing GR-KAN as a promising alternative for SE.