CMGAN: Conformer-based Metric GAN for Speech Enhancement

arXiv:2203.15149v4 Announce Type: replace-cross
Abstract: Recently, convolution-augmented transformer (Conformer) has achieved promising performance in automatic speech recognition (ASR) and time-domain speech enhancement (SE), as it can capture both local and global dependencies in the speech signal. In this paper, we propose a conformer-based metric generative adversarial network (CMGAN) for SE in the time-frequency (TF) domain. In the generator, we utilize two-stage conformer blocks to aggregate all magnitude and complex spectrogram information by modeling both time and frequency dependencies. The estimation …

abstract adversarial arxiv asr automatic speech recognition convolution cs.ai cs.lg cs.sd dependencies domain eess.as gan generative generative adversarial network global network paper performance recognition signal speech speech recognition transformer type