• Corpus ID: 1266554

Style Imitation and Chord Invention in Polyphonic Music with Exponential Families

@article{Hadjeres2016StyleIA,
  title={Style Imitation and Chord Invention in Polyphonic Music with Exponential Families},
  author={Ga{\"e}tan Hadjeres and Jason Sakellariou and François Pachet},
  journal={ArXiv},
  year={2016},
  volume={abs/1609.05152}
}
Modeling polyphonic music is a particularly challenging task because of the intricate interplay between melody and harmony. A good model should satisfy three requirements: statistical accuracy (capturing faithfully the statistics of correlations at various ranges, horizontally and vertically), flexibility (coping with arbitrary user constraints), and generalization capacity (inventing new material, while staying in the style of the training corpus). Models proposed so far fail on at least one… 

Figures and Tables from this paper

DeepBach: a Steerable Model for Bach Chorales Generation
TLDR
DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces, is introduced, which is capable of generating highly convincing chorales in the style of Bach.
Counterpoint by Convolution
TLDR
This model is an instance of orderless NADE, which allows more direct ancestral sampling, and finds that Gibbs sampling greatly improves sample quality, which is demonstrated to be due to some conditional distributions being poorly modeled.
Interactive Music Generation with Positional Constraints using Anticipation-RNNs
TLDR
This paper introduces a novel architecture called Anticipation-RNN which possesses the assets of the RNN-based generative models while allowing to enforce user-defined positional constraints and demonstrates its efficiency on the task of generating melodies satisfying positional constraints in the style of the soprano parts of the J.S. Bach chorale harmonizations.
Approachable Music Composition with Machine Learning at Scale
TLDR
The first AI-powered Google Doodle, the Bach Doodle, where users can create their own melody and have it harmonized by a machine learning model Coconet in the style of Bach is designed, and a simplified sheet-music based interface is designed.
BandNet: A Neural Network-based, Multi-Instrument Beatles-Style MIDI Music Composition Machine
TLDR
A recurrent neural network (RNN)-based MIDI music composition machine that is able to learn musical knowledge from existing Beatles' songs and generate music in the style of the Beatles with little human intervention is proposed.
Anticipation-RNN: enforcing unary constraints in sequence generation, with application to interactive music generation
TLDR
This article introduces a novel architecture called anticipation-RNN which possesses the assets of the RNN-based generative models while allowing to enforce user-defined unary constraints and demonstrates its efficiency on the task of generating melodies satisfying unary constraint in the style of the soprano parts of the J.S. Bach chorale harmonizations.
Music Transformer: Generating Music with Long-Term Structure
TLDR
It is demonstrated that a Transformer with the modified relative attention mechanism can generate minutelong compositions with compelling structure, generate continuations that coherently elaborate on a given motif, and in a seq2seq setup generate accompaniments conditioned on melodies.
Music Transformer
TLDR
It is demonstrated that a Transformer with the modified relative attention mechanism can generate minute-long compositions with compelling structure, generate continuations that coherently elaborate on a given motif, and in a seq2seq setup generate accompaniments conditioned on melodies.
Supervised Symbolic Music Style Translation Using Synthetic Data
TLDR
This study focuses on symbolic music with the goal of altering the 'style' of a piece while keeping its original 'content', and develops the first fully supervised algorithm for this task.
Groove2Groove: One-Shot Music Style Transfer With Supervision From Synthetic Data
TLDR
Groove2Groove is presented, a one-shot style transfer method for symbolic music, focusing on the case of accompaniment styles in popular music and jazz, using an encoder-decoder neural network for the task, along with a synthetic data generation scheme to supply it with parallel training examples.
...
...

References

SHOWING 1-10 OF 31 REFERENCES
Non-Conformant Harmonization: the Real Book in the Style of Take 6
TLDR
It is claimed that fioritures lead to musically more interesting harmonizations than previous approaches and why, and the validity of the approach is demonstrated by harmonizing a large corpus of standard leadsheets.
An Idiom-independent Representation of Chords for Computational Music Analysis and Generation
TLDR
The GCT representation of chord types is applied to a small set of examples from diverse musical idioms, and its output is illustrated and analysed showing its potential, especially, for computational music analysis & music information retrieval.
Probabilistic harmonization with fixed intermediate chord constraints
TLDR
The utilization of a well–studied probabilistic methodology, the hiddenMarkovmodel (HMM), in combination with additional constraints that incorporate intermediate fixed–chord constraints is discussed, and the constrained HMM (CHMM) is developed, harnessed with the novel general chord type (GCT) representation.
Markov Random Fields and Maximum Entropy Modeling for Music Information Retrieval
TLDR
This paper presents a framework for developing systems which combine a wide variety of non-independent features without having to make the independence assumption, and evaluates the system on the polyphonic theme similarity task over symbolic data.
Maximum Entropy Model for Melodic Patterns
TLDR
The main result is that this model can reproduce high-order patterns despite having a polynomial sample complexity, in contrast with the more traditionally used Markov models that have an exponential sample complexity.
HARMONET: A Neural Net for Harmonizing Chorales in the Style of J. S. Bach
TLDR
HARMONET, a system employing connectionist networks for music processing, is presented and is capable of producing four-part chorales in the style of J.S. Bach, given a one-part melody.
Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
TLDR
A probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences that outperforms many traditional models of polyphonic music on a variety of realistic datasets is introduced.
Modelling High-Dimensional Sequences with LSTM-RTRBM: Application to Polyphonic Music Generation
We propose an automatic music generation demo based on artificial neural networks, which integrates the ability of Long Short-Term Memory (LSTM) in memorizing and retrieving useful history
A Joyful Ode to Automatic Orchestration
  • F. Pachet
  • Computer Science
    ACM Trans. Intell. Syst. Technol.
  • 2017
TLDR
This article reports on a specific experiment in holistic music generation: the reorchestration of Beethoven’s Ode to Joy, the European anthem, in seven styles, produced with algorithms developed in the Flow Machines project and within a short time frame.
Computational Invention of Cadences and Chord Progressions by Conceptual Chord-Blending
TLDR
The framework builds on algebraic specifications, and solves two musicological problems, and automatically finds transitions between chord progressions of different keys or idioms and substitutes chords in a chord progression by other chords of a similar function as a means to create novel variations.
...
...