The aim is to implement a model that uses an LSTM to generate music.
You would like to create a jazz music piece. However, you don't know any instruments or music composition. Fortunately, you know deep learning and will solve this problem using an LSTM network.
You will train a network to generate novel jazz solos in a style representative of a body of performed work.
Tasks:
- Apply an LSTM to music generation.
- Generate your own jazz music with deep learning.
The ideas presented in this project came primarily from three computational music papers cited below.
- Ji-Sung Kim, 2016, deepjazz
- Jon Gillick, Kevin Tang and Robert Keller, 2009. Learning Jazz Grammars
- Robert Keller and David Morrison, 2007, A Grammatical Approach to Automatic Improvisation
- François Pachet, 1999, Surprising Harmonies