A neural network infers acoustic scene context to classify and remove out-of-context sounds as noise while preserving in-context sounds, outperforming non-contextual baselines on objective metrics across varied scenes.
My lips are concealed: Audio-visual speech enhancement through obstructions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Automatic Contextual Audio Denoising
A neural network infers acoustic scene context to classify and remove out-of-context sounds as noise while preserving in-context sounds, outperforming non-contextual baselines on objective metrics across varied scenes.