Progressive loss functions for speech enhancement with deep neural networks

Abstract The progressive paradigm is a promising strategy to optimize network performance for speech enhancement purposes. Recent works have shown different strategies improve the accuracy of solutions based on this mechanism. This paper studies using convolutional and residual neural architectures explores two criteria loss function optimization: weighted uniform progressive. work carries out evaluation simulated real samples with reverberation added noise REVERB VoiceHome datasets. Experimental results show variety achievements among optimization architectures. Results that design strengthens model increases robustness distortions due noise.