A single-layer LSTM learns to predict note sequences from a small pop MIDI dataset, reaching a training log-likelihood of -6.23 in 54 minutes.
Musical_Matrices,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LSTM Based Music Generation System
A single-layer LSTM learns to predict note sequences from a small pop MIDI dataset, reaching a training log-likelihood of -6.23 in 54 minutes.