MetricGAN+KAN: Kolmogorov-Arnold Networks in Metric-Driven Speech Enhancement Systems

Abstract

Neural-network-based speech enhancement (SE) approaches have shown to be particularly powerful in combination with perceptually motivated metrics to produce high-quality enhanced speech signals. Among these deep learning (DL)-based SE models, MetricGAN and its extension can generate output signals directly optimising quality metrics. The recently proposed Kolmogorov-Arnold networks (KANs) with learnable activation functions have shown great success in replacing multi-layer perceptrons (MLPs). This work proposes the use of KANs in a MetricGAN framework and analyses their performance in replacing different types of network layers. The best-performing proposed MetricGAN+KAN model uses approximately 80% fewer parameters and achieves 13.2% higher SE performance (measured by PESQ) on the Voicebank-DEMAND dataset, compared to the MetricGAN+ baseline.