A layer-wise correlation-permutation alignment lets a merged HuBERT-MERT encoder keep speech performance and improve music scores, beating linear interpolation by 19.5 points on the authors' aggregate score.
Ties- merging: Resolving interference when merging models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
A correlation-permutation approach for speech-music encoders model merging
A layer-wise correlation-permutation alignment lets a merged HuBERT-MERT encoder keep speech performance and improve music scores, beating linear interpolation by 19.5 points on the authors' aggregate score.