VAEs are trained on classical music to encode pieces into latent space and predict continuations, enabling composition of new music from existing pieces or random starts even with small training sets.
Generative timbre spaces with variational audio synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Classical Music Prediction and Composition by means of Variational Autoencoders
VAEs are trained on classical music to encode pieces into latent space and predict continuations, enabling composition of new music from existing pieces or random starts even with small training sets.