SPEECH ENHANCEMENT BASED ON DEEP FULLY CONVOLUTIONAL NEURAL ELASTIC NETWORK WCGAN-GP MODEL

Wasserstein generative adversarial network (WGAN) model has been widely used in speech enhancement, but WGAN has problems such as gradient explosion and unstable performance. This paper introduced gradient penalty (GP) and elastic network condition constraints, and optimized the generator and discriminator into deep fully convolutional neural networks (DFCNN) structure, and proposed a kind of Wasserstein conditional gradient penalty generative adversarial Elastic network (WCGAN-GP) model based on DFCN. The improved model could reach the real Lipschitz constraints, improve the controllability, stability and feature extraction capabilities, and optimize training faster. The experiment enhanced the speech under different noise conditions with the improved model and WGAN. The results verify the superiority of the improved model in speech enhancement.