A fuzzy rule model for high level musical features on automated composition systems

Algorithmic composition systems are now well-understood. However, when they are used for specific tasks like creating material for a part of a piece, it is common to prefer, from all of its possible outputs, those exhibiting specific properties. Even though the number of valid outputs is huge, many times the selection is performed manually, either using expertise in the algorithmic model, by means of sampling techniques, or some times even by chance. Automations of this process have been done traditionally by using machine learning techniques. However, whether or not these techniques are really capable of capturing the human rationality, through which the selection is done, to a great degree remains as an open question. The present work discusses a possible approach, that combines expert’s opinion and a fuzzy methodology for rule extraction, to model high level features. An early implementation able to explore the universe of outputs of a particular algorithm by means of the extracted rules is discussed. The rules search for objects similar to those having a desired and pre-identified feature. In this sense, the model can be seen as a finder of objects with specific properties.