Entry
DeepBach: a Steerable Model for Bach chorales generation by Gaëtan Hadjeres, François Pachet
Simple Title
Hadjeres, Gaëtan, François Pachet, and Frank Nielsen, "Deepbach: a steerable model for bach chorales generation.", International Conference on Machine Learning. PMLR, (2017)
Type
Paper
Year
2017
Posted at
December 19, 2016
Tags
music
Overview
DeepBachという名前が示す通り、バッハの賛美歌を学習した統計的なモデルでバッハ風の楽曲を生成する.
Abstract
This paper introduces DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces. We claim that, after being trained on the chorale harmonizations by Johann Sebastian Bach, our model is capable of generating highly convincing chorales in the style of Bach. DeepBach's strength comes from the use of pseudo-Gibbs sampling coupled with an adapted representation of musical data. This is in contrast with many automatic music composition approaches which tend to compose music sequentially. Our model is also steerable in the sense that a user can constrain the generation by imposing positional constraints such as notes, rhythms or cadences in the generated score. We also provide a plugin on top of the MuseScore music editor making the interaction with DeepBach easy to use.
Architecture
バッハの賛美歌曲 352曲とそれを転調させたもの2503曲を元に、ニューラルネットワークを学習。メロディーを与えるとバッハ風にハーモナイズされた他の3つのパートが生成される.
Results
生成された楽曲がどのくらいオリジナルのバッハの楽曲に近いかをテストするために、400名のプロのミュージシャンや音楽を学ぶ学生を含む1600人以上を対象にテストを実施. 50%前後の割合で、オリジナルだと間違う程度の精度で楽曲を生成できていることがわかった。