Piano Genie
This addresses the challenge of making music creation accessible to non-experts, though it is an incremental application of existing neural network techniques to a specific domain.
The authors tackled the problem of enabling non-musicians to improvise piano music by developing Piano Genie, a controller that maps eight-button inputs to plausible piano sequences in real time, using a trained recurrent neural network autoencoder with discrete bottlenecks.
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.