CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement

arXiv:2209.11112v3 Announce Type: replace-cross
Abstract: In this work, we further develop the conformer-based metric generative adversarial network (CMGAN) model for speech enhancement (SE) in the time-frequency (TF) domain. This paper builds on our previous work but takes a more in-depth look by conducting extensive ablation studies on model inputs and architectural design choices. We rigorously tested the generalization ability of the model to unseen noise types and distortions. We have fortified our claims through DNS-MOS measurements and listening tests. Rather …

abstract adversarial arxiv cs.ai cs.lg cs.sd design domain eess.as gan generative generative adversarial network inputs look network paper speech studies type work