Options
Towards end-to-end raw audio music synthesis
Publikationstyp
Conference Paper
Publikationsdatum
2018-10
Sprache
English
First published in
Number in series
11141 LNCS
Start Page
137
End Page
146
Citation
27th International Conference on Artificial Neural Networks (ICANN 2018)
Contribution to Conference
Publisher DOI
Scopus ID
In this paper, we address the problem of automated music synthesis using deep neural networks and ask whether neural networks are capable of realizing timing, pitch accuracy and pattern generalization for automated music generation when processing raw audio data. To this end, we present a proof of concept and build a recurrent neural network architecture capable of generalizing appropriate musical raw audio tracks.
Schlagworte
Music synthesis
Recurrent neural networks