Speech Enhancement Using Dilated Wave-U-Net: an Experimental Analysis

Speech enhancement is a relevant component in many real-world applications such as hearing aid devices, mobile telecommunications, and healthcare applications. In this paper, we investigate on the Dilated Wave-U-Net model: a recently proposed end-to-end neural speech enhancement approach based on the Wave-U-Net architecture. We evaluate the performance of the model on two datasets: the public VCTK dataset, and a contaminated version of the Librispeech dataset. In particular, we experiment on using alternative losses based on the MSE loss, L1 norm, and on a combination of L1 and MSE losses. Results show that the Dilated Wave-U-Net architecture outperforms other state-of-the-art methods in terms of intelligibility and quality metrics on both datasets and that MSE loss is the most performing one.