SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement

13 Jun 2020 Luka Chkhetiani Levan Bejanidze

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose that it is possible to transfer the MelGAN's [3] robustness in learning speech features to speech enhancement and noise reduction domain without any model modification tasks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Speech Enhancement Librispeech SE-MelGAN Audio Quality MOS 3.1 # 1

Methods used in the Paper