A three-stage fusion of a sparse compression separator, an SSL-conditioned codec-token generator, and a fusion network achieves third place in URGENT 2025 and improves perceptual metrics with a modest fidelity trade-off.
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
-
FUSE: Universal Speech Enhancement using Multi-Stage Fusion of Sparse Compression and Token Generation Models for the URGENT 2025 Challenge
A three-stage fusion of a sparse compression separator, an SSL-conditioned codec-token generator, and a fusion network achieves third place in URGENT 2025 and improves perceptual metrics with a modest fidelity trade-off.