A three-part components loss for mask-based speech enhancement outperforms MSE and perceptual-weighting baselines on PESQ and SNR.
Speech Enhancement by MAP Spectra l Am- plitude Estimation Using a Super-Gaussian Speech Model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Components Loss for Neural Networks in Mask-Based Speech Enhancement
A three-part components loss for mask-based speech enhancement outperforms MSE and perceptual-weighting baselines on PESQ and SNR.