DeepBach: a Steerable Model for Bach Chorales Generation

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.

10 pages, ICML2017 version

References in corpus (5)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Improved contact prediction in proteins: Using pseudolikelihoods to infer Potts models
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Learning Longer Memory in Recurrent Neural Networks
• Style Imitation and Chord Invention in Polyphonic Music with Exponential Families

Cited by in corpus (18)

• MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
• Imposing higher-level Structure in Polyphonic Music Generation using Convolutional Restricted Boltzmann Machines and Constraints
• Learning a Latent Space of Multitrack Measures
• Exploring Variational Auto-Encoder Architectures, Configurations, and Datasets for Generative Music Explainable AI
• SING: Symbol-to-Instrument Neural Generator
• Learning Style-Aware Symbolic Music Representations by Adversarial Autoencoders
• Sampling Variations of Lead Sheets
• Dance Dance Convolution
• Semi-Recurrent CNN-based VAE-GAN for Sequential Data Generation
• A Framework for Automated Pop-song Melody Generation with Piano Accompaniment Arrangement
• DeepDrum: An Adaptive Conditional Neural Network
• Deep Segment Hash Learning for Music Generation
• Multiple scaling behavior and nonlinear traits in music scores
• Classical Music Composition Using State Space Models
• Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
• Automatic Realistic Music Video Generation from Segments of Youtube Videos
• Markov-switching State Space Models for Uncovering Musical Interpretation
• Harmonic Recomposition using Conditional Autoregressive Modeling