A 3.58M-parameter, two-stage causal speech enhancer adds a GAN second stage to DeepFilterNet2 and improves NISQA-MOS on the URGENT test set.
As a result, the generator learns the clean speech distribu- tion conditioned on the noisy speech and the intermediate en- hanced speech, i.e
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration
A 3.58M-parameter, two-stage causal speech enhancer adds a GAN second stage to DeepFilterNet2 and improves NISQA-MOS on the URGENT test set.