On the Stylistic Evolution of a Society of Virtual Melody Composers

@inproceedings{Velardo2015OnTS,
  title={On the Stylistic Evolution of a Society of Virtual Melody Composers},
  author={Valerio Velardo and M. Vallati},
  booktitle={EvoMUSART},
  year={2015}
}
In the field of computational creativity, the area of automatic music generation deals with techniques that are able to automatically compose human-enjoyable music. Although investigations in the area started recently, numerous techniques based on artificial intelligence have been proposed. Some of them produce pleasant results, but none is able to effectively evolve the style of the musical pieces generated. 
1 Citations

On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study

TLDR
This work considers a society of creative agents with varying skills and aesthetic preferences able to interact with each other by exchanging artifacts or through collaboration and observes that peer models guide the agents to more beneficial collaborations.

References

SHOWING 1-10 OF 23 REFERENCES

Automatic Melody Composition and Evolution: A Cognitive-Based Approach

TLDR
A memetic model for music composition is proposed, which considers both psychological and social levels and is the first system known to be aware of which can evolve its own compositional style.

Modeling Musical Style with Language Models for Composer Recognition

TLDR
An application of language modeling using n-grams to model the style of different composers using a corpus of 5 composers from the Baroque and Classical periods shows that language modeling is a suitable tool for modeling musical style, even when the styles of the different datasets are affected by several factors.

A Machine Learning Approach to Musical Style Recognition

TLDR
This work demonstrates that machine learning can be used to build effective style classifiers for interactive performance systems and presents an analysis explaining why these techniques work so well when hand-coded approaches have consistently failed.

On the evolution of music in a society of self-taught digital creatures

TLDR
This paper introduces a model where a society of distributed and autonomous but co-operative agents evolves repertoires of short melodies from scratch, by interacting with one another, and addresses the possibility of implementing collective generative music systems, using virtual musicians who learn how to compose and play by themselves and with people interacting with them.

Automatic Modeling of Musical Style

TLDR
Two methods for unsupervised learning of musical style are described and compared, both of which perform analyses of musical sequences and then compute a model from which new interpretations / improvisations close to the original's style can be generated.

A Memetic Approach to the Evolution of Rhythms in a Society of Software Agents

TLDR
RGeme (Rhythmic Meme Generator), an artificial intelligence system for the composition of rhythmic streams inspired by Richard Dawkin's theory of memes, is developed based on intelligent agents that learn from examples and interact by generating rhythms.

The Memetics of Music: A Neo-Darwinian View of Musical Structure and Culture

Contents: Preface Introduction: biological and socio-cultural evolution Memory, replication and style: memes in music I Replicating sonorities, replicating hierarchies: memes in music II Evolutionary

AI Methods in Algorithmic Composition: A Comprehensive Survey

TLDR
This survey aims to be a comprehensive account of research on algorithmic composition, presenting a thorough view of the field for researchers in Artificial Intelligence.

Musical Style Classification from Symbolic Data: A Two-Styles Case Study

TLDR
The classification of monophonic melodies from two different musical styles is studied using different classification methods: Bayesian classifier, a k-NN classifiers, and self-organising maps (SOM).

Rhythms as emerging structures

Rhythm has traditionally been considered a fundamental dimension of music. In the context of musical content feature extraction, in particular for music catalogues, the rhythmic dimension has up to