LGHCSDASMLOct 11, 2018

Piano Genie

arXiv:1810.05246v248 citations
Originality Synthesis-oriented
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes