A coarse-to-fine cosine similarity loss with a dynamic perceptual loss improves objective speech enhancement scores on the Valentini benchmark.
Particularly in generative models, the proposed dynamic per- ceptual loss could further improve the accuracy obtained from optimizing the cosine similarity loss from coarse to fine
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Coarse-to-fine Optimization for Speech Enhancement
A coarse-to-fine cosine similarity loss with a dynamic perceptual loss improves objective speech enhancement scores on the Valentini benchmark.