SEDM couples separate magnitude and phase diffusion networks with real-noise corruption and a cycle-consistency loss, reporting improved speech-enhancement metrics on IEEE, TIMIT, VCTK, and DNS test sets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Complex-Cycle-Consistent Diffusion Model for Monaural Speech Enhancement
SEDM couples separate magnitude and phase diffusion networks with real-noise corruption and a cycle-consistency loss, reporting improved speech-enhancement metrics on IEEE, TIMIT, VCTK, and DNS test sets.