Name
Title | ||
|---|---|---|
<Emphasis Type="Italic">This time with feeling:</Emphasis> learning expressive musical performance |
Abstract | ||
|---|---|---|
Music generation has generally been focused on either creating scores or interpreting them. We discuss differences between these two problems and propose that, in fact, it may be valuable to work in the space of direct performance generation: jointly predicting the notes and also their expressive timing and dynamics. We consider the significance and qualities of the dataset needed for this. Having identified both a problem domain and characteristics of an appropriate dataset, we show an LSTM-based recurrent network model that subjectively performs quite well on this task. Critically, we provide generated examples. We also include feedback from professional composers and musicians about some of these examples. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1007/s00521-018-3758-9 | Neural Computing and Applications |
Keywords | DocType | Volume |
Music generation, Deep learning, Recurrent neural networks, Artificial intelligence | Journal | 32 |
Issue | ISSN | Citations |
4 | 1433-3058 | 1 |
PageRank | References | Authors |
0.48 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sageev Oore | 1 | 101 | 18.63 |
| Ian Simon | 2 | 675 | 46.26 |
| Sander Dieleman | 3 | 1 | 0.48 |
| Douglas Eck | 4 | 748 | 64.84 |
| Karen Simonyan | 5 | 12058 | 446.84 |