Automatic melody composition based on a probabilistic model of music style and harmonic rules

@article{Roig2014AutomaticMC,
  title={Automatic melody composition based on a probabilistic model of music style and harmonic rules},
  author={Carles Roig and Lorenzo J. Tard{\'o}n and Isabel Barbancho and Ana M. Barbancho},
  journal={Knowl. Based Syst.},
  year={2014},
  volume={71},
  pages={419-434}
}
Abstract The aim of the present work is to perform a step towards the design of specific algorithms and methods for automatic music generation. A novel probabilistic model for the characterization of music learned from music samples is designed. This model makes use of automatically extracted music parameters, namely tempo, time signature, rhythmic patterns and pitch contours, to characterize music. Specifically, learned rhythmic patterns and pitch contours are employed to characterize music… 
A Parameterized Harmony Model for Automatic Music Completion
In this paper, we propose harmony generation according to user input parameters based on fundamental harmonic properties as a new approach to the problem of automatic music completion (the automatic
Statistics-Based Music Generation Approach Considering Both Rhythm and Melody Coherence
TLDR
This paper presents a music generation method which is an extension of a previously presented method that generates coherent melodies using a melodic coherence structure extracted from a template piece that adds the generation of the rhythmic content of the melodies.
A Music Generation Model for Robotic Composers
TLDR
This paper detailedly state how to transform the prior knowledge about music theory into a reasonable metric, and proposes a sample metric for reference, and generates a set of music pieces which fully satisfy the need of quality and creativity.
Polyphonic Voicing Optimization for Automatic Music Completion
  • Christoph M. Wilk, S. Sagayama
  • Computer Science
    2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2019
TLDR
A new polyphonic voicing model for automatically completing four-part chorales is presented based on a hidden Markov model and what the authors call correction factors, which are trainable functions that efficiently capture the context of a voicing in order to account for a multitude of music theoretical rules without having to resort to a rule-based system.
34 34
Automatic music generation systems have gained in popularity and sophistication as advances in cloud computing have enabled large-scale complex computations such as deep models and optimization
A multi-objective evolutionary approach to automatic melody generation
TLDR
A novel multi-objective evolutionary approach to automatic melody composition in order to produce a variety of melodies at once and analysis of composition results proves that the proposed approach generates a set of pleasant and diverse melodies.
A non-homogeneous beat-based harmony Markov model
TLDR
This paper shows how to create a non-homogeneous Markov chain to automatically generate harmonic progressions by building a temporal reference of the internal beat structure of music to guide the progressions.
MorpheuS: Generating Structured Music with Constrained Patterns and Tension
TLDR
The MorpheuS music generation system, presented, has the ability to generate polyphonic pieces with a given tension profile and long- and short-term repeated pattern structures and is particularly useful in a game or film music context.
Harmony and Voicing Interpolation for Automatic Music Composition Assistance
  • Christoph M. Wilk, S. Sagayama
  • Computer Science
    2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
  • 2018
TLDR
A composition assistant system that allows a user to freely define any part of a four-part chorale to be composed, be it harmony or partial melodies for up to four voices, and interpolates the user input and yields a complete four- part voicing including the underlying harmony progression.
Interactive Arrangement of Chords and Melodies Based on a Tree-Structured Generative Model
TLDR
An interactive music composition system that assists a user in refining chords and melodies by generating chords for melodies (harmonization) and vice versa (melodization) is described and the subjective experimental result showed the effectiveness of the proposed system.
...
1
2
3
4
...

References

SHOWING 1-10 OF 58 REFERENCES
Algorithmic compositions based on discovered musical patterns
TLDR
An approach utilizes the data mining techniques in order to discover the styled rules of music composition characterized by music structures, melody styles and motifs and to create a new music object of which style is similar to the given music objects based on the discovered composition rules.
Algorithmic Composition: Paradigms of Automated Music Generation
TLDR
This is the first book to provide a detailed overview of prominent procedures of algorithmic composition in a pragmatic way rather than by treating formalizable aspects in single works.
Automatic Transcription of Melody, Bass Line, and Chords in Polyphonic Music
TLDR
The method is computationally efficient and allows causal implementation, so it can process streaming audio, and may be used in music analysis, music information retrieval from large music databases, content-based audio processing, and interactive music systems.
Music Generation from Statistical Models
TLDR
This paper presents several methods for sampling from an analytic statistical model, and proposes a new approach that maintains the intra opus pattern repetition within an extant piece.
ESTIMATION OF TEMPO, MICRO TIME AND TIME SIGNATURE FROM PERCUSSIVE MUSIC
Tempo, micro time and time signature are basic rhythmic features for a wide range of music. Their automated extraction from music is needed for a number of applications, e.g. automatic transcription
Computer Modeling of Musical Intelligence in EMI
TLDR
The algorithm presented in this article reflects the author's approach to music composition and hence represents one "simulation of musical thinking." Implementations of this algorithm create new compositions by way of a reflexive pattern-matcher combined with an augmented transition network (ATN).
Inmamusys: Intelligent multiagent music system
TLDR
A high modular system that composes music on its own by using Experts Systems technology and rule-based systems principles and investigating relationships between computers and emotions and how the latter can be represented into the former.
From MIDI to Traditional Musical Notation
In this paper a system that is designed to extract the musical score from a MIDI performance is described. The proposed system comprises of a number of modules that perform the following tasks:
Statistical description models for melody analysis and characterization
The analysis of melodies symbolically represented as digital scores (standard MIDI files) is studied. A number of melodic, harmonic, and rhythmic statistical descriptors are computed. Their
Signal Processing for Music Analysis
TLDR
It is demonstrated that, to be successful, music audio signal processing techniques must be informed by a deep and thorough insight into the nature of music itself.
...
1
2
3
4
5
...