*Article* **A Multi-Resolution Approach to GAN-Based Speech Enhancement**

**Hyung Yong Kim, Ji Won Yoon, Sung Jun Cheon, Woo Hyun Kang and Nam Soo Kim \***

> Department of Electrical and Computer Engineering and the Institute of New Media and Communications, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea; hykim@hi.snu.ac.kr (H.Y.K.); jwyoon@hi.snu.ac.kr (J.W.Y.); sjcheon@hi.snu.ac.kr (S.J.C.); whkang@hi.snu.ac.kr (W.H.K.)

**\*** Correspondence: nkim@snu.ac.kr; Tel.: +82-2-880-8419

**Abstract:** Recently, generative adversarial networks (GANs) have been successfully applied to speech enhancement. However, there still remain two issues that need to be addressed: (1) GAN-based training is typically unstable due to its non-convex property, and (2) most of the conventional methods do not fully take advantage of the speech characteristics, which could result in a sub-optimal solution. In order to deal with these problems, we propose a progressive generator that can handle the speech in a multi-resolution fashion. Additionally, we propose a multi-scale discriminator that discriminates the real and generated speech at various sampling rates to stabilize GAN training. The proposed structure was compared with the conventional GAN-based speech enhancement algorithms using the VoiceBank-DEMAND dataset. Experimental results showed that the proposed approach can make the training faster and more stable, which improves the performance on various metrics for speech enhancement.

**Keywords:** speech enhancement; generative adversarial network; relativistic GAN; convolutional neural network
