Miguel Molina-Solana

We present GenoMus, a new model for artificial musical creativity based on a procedural approach, able to represent and learn compositional techniques behind a musical score. The aim of this model is to build a framework for automatic creativity, easily adaptable to other domains beyond music. The core of GenoMus is a functional grammar designed to cover a wide range of styles, integrating traditional and contemporary composing techniques. In its encoded form, both composing methods and music scores are represented as one-dimensional arrays of normalized values. On the other hand, the decoded form of GenoMus grammar is human-readable, allowing manual edition and the implementation of user-defined processes. Musical procedures (genotypes) are defined as functional trees, able to generate musical scores (phenotypes). Each subprocess uses the same generic functional structure, no matter what time scale, polyphonic structure, traditional or algorithmic process is being employed. The goal of this highly homogeneous and modular approach is to simplify metaprogramming and to maximize search space. This abstract and compact representation of musical knowledge as pure numeric arrays is optimized for the application of different machine learning paradigms.

@article{LopezMontes2022,
  author = {López-Montes, José and Molina-Solana, Miguel and Fajardo, Waldo},
  title = {GenoMus: Representing Procedural Musical Structures with an Encoded Functional Grammar Optimized for Metaprogramming and Machine Learning},
  journal = {Applied Sciences},
  year = {2022},
  volume = {12},
  number = {16},
  articleno = {8322},
  doi = {10.3390/app12168322},
  comment = {},
  timestamp = {34}
}