Sergan: Speech Enhancement Using Relativistic Generative Adversarial Networks with Gradient Penalty

Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Recently, conditional generative adversarial networks (cGANs) have shown promise in addressing the phase mismatch problem by directly mapping the raw noisy speech waveform to the underlying clean speech signal. However, stabilizing and training cGAN systems is difficult and they still fall short of the performance achieved by spectral enhancement approaches. This paper introduces relativistic GANs with a relativistic cost function at its discriminator and gradient penalty to improve time-domain speech enhancement. Simulation results show that relativistic discriminators provide a more stable training of cGANs and yield a better generator network for improved speech enhancement performance.

1. INTRODUCTION

Speech enhancement systems aim to improve the quality and intelligibility of acquired speech signals by removing artefacts caused by background noise or other interferences such as room reverberation. Recently, deep neural network (DNN)-based approaches gained success in speech enhancement due to their powerful modeling capabilities [1]–[5].