TS-URGENet, a filling-separation-restoration cascade with metric-aware fine-tuning, places 2nd in the URGENT 2025 universal speech enhancement challenge.
1, our proposed framework is composed of three parts: filling, separation, and restoration stages
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network
TS-URGENet, a filling-separation-restoration cascade with metric-aware fine-tuning, places 2nd in the URGENT 2025 universal speech enhancement challenge.