A cross-modal model extracts performance style from audio and uses it to generate matching piano arrangements from lead sheets, with style transfer and audio-to-MIDI retrieval.
Experiments demonstrate that it outperforms existing audio-to-symbolic mod- els, including both disentanglement-based methods and standard LM approaches
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping
A cross-modal model extracts performance style from audio and uses it to generate matching piano arrangements from lead sheets, with style transfer and audio-to-MIDI retrieval.