A generative diffusion speech enhancement model preserves syllable stress better than discriminative enhancers for non-native English speech, and human perception matches automatic stress detection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating the Impact of Discriminative and Generative E2E Speech Enhancement Models on Syllable Stress Preservation
A generative diffusion speech enhancement model preserves syllable stress better than discriminative enhancers for non-native English speech, and human perception matches automatic stress detection.