Abstract | ||
---|---|---|
We present Piano Genie, an intelligent controller which allows non-musicians to improvise on the piano. With Piano Genie, a user performs on a simple interface with eight buttons, and their performance is decoded into the space of plausible piano music in real time. To learn a suitable mapping procedure for this problem, we train recurrent neural network autoencoders with discrete bottlenecks: an encoder learns an appropriate sequence of buttons corresponding to a piano piece, and a decoder learns to map this sequence back to the original piece. During performance, we substitute a user's input for the encoder output, and play the decoder's prediction each time the user presses a button. To improve the intuitiveness of Piano Genie's performance behavior, we impose musically meaningful constraints over the encoder's outputs.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3301275.3302288 | Proceedings of the 24th International Conference on Intelligent User Interfaces |
Keywords | DocType | Volume |
augmented intelligence, discrete representation learning, generative modeling, music, piano, real-time, web | Conference | abs/1810.05246 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chris Donahue | 1 | 0 | 2.03 |
Ian Simon | 2 | 675 | 46.26 |
Sander Dieleman | 3 | 2607 | 102.93 |