OmniGSE combines a continuous feature enhancement stage with a RootLM/BranchLM token generation stage to improve general speech enhancement on mixed distortions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Continuous to Discrete: Cross-Domain Collaborative General Speech Enhancement via Hierarchical Language Models
OmniGSE combines a continuous feature enhancement stage with a RootLM/BranchLM token generation stage to improve general speech enhancement on mixed distortions.