Formalizing Fado: A contribution to automatic song making

This article is a contribution to the formalisation of the process of song composition, focusing on a case study: Portuguese fado (a performance practice). Based on previous musicological studies, we describe a theoretical model which is parametrised using empirical data retrieved from a representative symbolic corpus. Starting from the model, we present the formalisation of a symbolic artificial intelligence implemented as a generative system. This system is able to automatically generate instrumental music based on the musics and vocal sounds typically associated with fado’s practice. The output of the system is evaluated resorting both to a supervised classification system and to a quasi-Turing test. We conclude that the output of our system approaches the one from the corpus and has relevant pleasantness to human listeners.