A diffusion speech enhancement model conditioned on wav2vec 2.0 features via FiLM achieves a 0.4 PESQ gain on standard datasets.
Title resolution pending
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
-
Bridging Self-Supervised Learning and Speech Enhancement: A Wav2Vec2-Conditioned Framework
A diffusion speech enhancement model conditioned on wav2vec 2.0 features via FiLM achieves a 0.4 PESQ gain on standard datasets.