TLDR: During my experiments with discrete NN architectures I made a VAE neural network for stylized midi music generation. Later, we used it to make several public performances, such as a live performance in style of Alexander Scriabin by a theremin with orchestra on the opening of Yet Another Conference (an annual IT conference organized in Moscow by Yandex) or a performance of neuro-jazz track by Russian jazz trumpet player Vadim Eilenkrig on a closed party to celebrate 100 year anniversary of jazz.
After several experiments with neural network language modeling, I decided to go deeper and try some more different architectures. As a model task, I took the MIDI music generation since a lot of such data is available online and it’s relatively easy to parse. I collected ~4Gb of MIDI files and spent several months on parsing and cleaning this data — autoselecting the solo track, removing degenerated tracks, detecting bass and drum tracks and so on.
Anyway, I got several thousands of clean tracks to learn from and started some research on different RNN architectures. I started with LM, then tried some seq2seq approaches and finally managed to teach a more or less stable VAE network. Here is a short video of the exploration of this VAE space:
Among the other experiments I made were two additional seq2seq based networks — bassNN and drumNN, to provide some orchestration to the solo, generated by the main network.
* * *
As I started to share some results of my experiments, it appears a bunch of music artists interested in them, so with a help of a friend on mine, Ivan Yamshchikov, we made several performances and speeches for an art public. Among them were:
- A live performance in style of Alexander Scriabin by a theremin with orchestra on the opening of Yet Another Conference (an annual IT conference organized in Moscow by Yandex) in front of 2000 visitors. The track was arranged by Maria Chernova, Moscow-based artist, composer, and expert working with Scriabin legacy. Check out the video of this performance.
- We teamed up with Russian jazz trumpet player Vadim Eilenkrig and created together a jazz track for Wild Turkey bourbon event by Rodnya Creative PR Studio to celebrate 100 year anniversary of jazz. Check this video to listen to this track (in Russian with English subtitles).
- French composer and sound producer Jean-Christophe Cheneval made several arrangements of our “neuro-Bach” tracks. Listen to them here or here.
- Here is also Ivan’s talk “Automated music generation with artificial neural networks” on IDAGIO Tech Talks in Berlin.
More to come :)