Noise augmentation yields the largest gains for pathological speech enhancement while generative methods can degrade performance, though a gap to neurotypical speech remains.
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Data Augmentation for Pathological Speech Enhancement
Noise augmentation yields the largest gains for pathological speech enhancement while generative methods can degrade performance, though a gap to neurotypical speech remains.