Layer-wise probing of MusicFM and MuQ shows acoustic-to-semantic feature progression across layers, and single-layer selection often outperforms all-layer aggregation on MIR tasks.
One of the most significant advantages of SSL mod- els is their ability to leverage unlabeled audio data, enabling the possibility of training with large-scale datasets
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
support 1representative citing papers
citing papers explorer
-
Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
Layer-wise probing of MusicFM and MuQ shows acoustic-to-semantic feature progression across layers, and single-layer selection often outperforms all-layer aggregation on MIR tasks.