A music BERT with bounded token denoising and pianoroll prediction beats standard masked-language pre-training on a new 12-task symbolic music benchmark.
For reference, we show the state-of-the-art (SOTA) performance of the tasks in the last row, if available
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
background 1representative citing papers
citing papers explorer
-
Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Prediction
A music BERT with bounded token denoising and pianoroll prediction beats standard masked-language pre-training on a new 12-task symbolic music benchmark.