Using the model's own encoder as a feature loss improves perceptual quality and iterative stability of a speech enhancement model compared with a WavLM-based loss.
A critical component in training enhancement models is the choice of loss function, which directly influences the quality and generaliza- tion of enhanced output [6, 7]
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
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Model as Loss: A Self-Consistent Training Paradigm
Using the model's own encoder as a feature loss improves perceptual quality and iterative stability of a speech enhancement model compared with a WavLM-based loss.